publications

@inproceedings{pati_dmelodies_2020,

title = {dMelodies: A Music Dataset for Disentanglement Learning},

author = {Ashis K Pati and Siddharth Gururani and Alexander Lerch},

url = {https://musicinformatics.gatech.edu/wp-content_nondefault/uploads/2020/08/Pati-et-al.-2020-dMelodies-A-Music-Dataset-for-Disentanglement-Lea.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {International Society for Music Information Retrieval (ISMIR)},

address = {Montreal},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hung_multi-task_2020,

title = {Multi-Task Learning for Instrument Activation Aware Music Source Separation},

author = {Yun-Ning Hung and Alexander Lerch},

url = {https://musicinformatics.gatech.edu/wp-content_nondefault/uploads/2020/08/Hung-and-Lerch-2020-Multi-Task-Learning-for-Instrument-Activation-Awar.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {International Society for Music Information Retrieval (ISMIR)},

address = {Montreal},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{manjunath_automatic_2020,

title = {Automatic Classification of Live and Studio Audio Recordings using Convolutional Neural Networks},

author = {Tejas Manjunath and Jeet Pawani and Alexander Lerch},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the Audio Engineering Society Convention},

address = {New York},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{yang_remixing_2020,

title = {Remixing Music with Visual Conditioning},

author = {Li-Chia Yang and Alexander Lerch},

url = {https://musicinformatics.gatech.edu/wp-content_nondefault/uploads/2020/10/Yang-and-Lerch-2020-Remixing-Music-with-Visual-Conditioning.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the IEEE International Symposium on Multimedia (ISM)},

publisher = {Institute of Electrical and Electronics Engineers (IEEE)},

address = {Naples, Italy},

abstract = {We propose a visually conditioned music remixing system by incorporating deep visual and audio models. The method is based on a state of the art audio-visual source separation model which performs music instrument source separation with video information. We modified the model to work with user-selected images instead of videos as visual input during inference to enable separation of audio-only content. Furthermore, we propose a remixing engine that generalizes the task of source separation into music remixing. The proposed method is able to achieve improved audio quality compared to remixing performed by the separate-and-add method with a state-of-the-art audio-visual source separation model.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chen_melody-conditioned_2020,

title = {Melody-Conditioned Lyrics Generation with SeqGANs},

author = {Yihao Chen and Alexander Lerch},

url = {https://musicinformatics.gatech.edu/wp-content_nondefault/uploads/2020/10/Chen-and-Lerch-2020-Melody-Conditioned-Lyrics-Generation-with-SeqGANs.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the IEEE International Symposium on Multimedia (ISM)},

publisher = {Institute of Electrical and Electronics Engineers (IEEE)},

address = {Naples, Italy},

abstract = {Automatic lyrics generation has received attention from both music and AI communities for years. Early rule-based approaches havetextasciitilde---due to increases in computational power and evolution in data-driven models---textasciitildemostly been replaced with deep-learning-based systems. Many existing approaches, however, either rely heavily on prior knowledge in music and lyrics writing or oversimplify the task by largely discarding melodic information and its relationship with the text. We propose an end-to-end melody-conditioned lyrics generation system based on Sequence Generative Adversarial Networks (SeqGAN), which generates a line of lyrics given the corresponding melody as the input. Furthermore, we investigate the performance of the generator with an additional input condition: the theme or overarching topic of the lyrics to be generated. We show that the input conditions have no negative impact on the evaluation metrics while enabling the network to produce more meaningful results.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{guan_learning_2019,

title = {Learning Strategies for Voice Disorder Detection},

author = {Hongzhao Guan and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/01/Guan-and-Lerch-2019-Learning-Strategies-for-Voice-Disorder-Detection.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the International Conference on Semantic Computing (ICSC)},

abstract = {Voice disorder is a health issue that is frequently encountered, however, many patients either cannot afford to visit a professional doctor or neglect to take good care of their voice. In order to give a patient a preliminary diagnosis without using professional medical devices, previous research has shown that the detection of voice disorders can be carried out by utilizing machine learning and acoustic features extracted from voice recordings. Considering the increasing popularity of deep learning and feature learning, this study explores the possibilities of using these methods to assign voice recordings into one of the two classes\textemdashNormal and Pathological. While the results show the general viability of deep learning and feature learning for the automatic recognition of voice disorder, they also demonstrate the shortcomings of the existing datasets for this task such as insufficient dataset size and lack of generality.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{swaminathan_improving_2019,

title = {Improving Singing Voice Separation using Attribute-Aware Deep Network},

author = {Rupak Vignesh Swaminathan and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/01/Swaminathan-and-Lerch-2019-Improving-Singing-Voice-Separation-using-Attribute.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the International Workshop on Multilayer Music Representation and Processing (MMRP)},

address = {Milan, Italy},

abstract = {Singing Voice Separation (SVS) attempts to separate the predominant singing voice from a polyphonic musical mixture. In this paper, we investigate the effect of introducing attribute-specific information, namely, the frame level vocal activity information as an augmented feature input to a Deep Neural Network performing the separation. Our study considers two types of inputs, i.e, a ground-truth based ‘oracle’ input and labels extracted by a state-of-the-art model for singing voice activity detection in polyphonic music. We show that the separation network informed of vocal activity learns to differentiate between vocal and non-vocal regions. Such a network thus reduces interference and artifacts better compared to the network agnostic to this side information. Results on the MIR1K dataset show that informing the separation network of vocal activity improves the separation results consistently across all the measures used to evaluate the separation quality.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{qin_tuning_2019,

title = {Tuning Frequency Dependency in Music Classification},

author = {Yi Qin and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/04/Qin-and-Lerch-2019-Tuning-Frequency-Dependency-in-Music-Classificatio.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the International Conference on Acoustics Speech and Signal Processing (ICASSP)},

address = {Brighton, UK},

abstract = {Deep architectures have become ubiquitous in Music Information Retrieval (MIR) tasks, however, concurrent studies still lack a deep understanding of the input properties being evaluated by the networks. In this study, we show by the example of a Music Genre Classification system the potential dependency on the tuning frequency, an irrelevant and confounding variable. We generate adversarial samples through pitch-shifting the audio data and investigate the classification accuracy of the output depending on the pitch shift. We find the accuracy to be periodic with a period of one semitone, indicating that the system is utilizing tuning information. We show that proper data augmentation including pitch-shifts smaller than one semitone helps minimizing this problem and point out the need for carefully designed augmentation procedures in related MIR tasks.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gururani_comparison_2019,

title = {A Comparison of Music Input Domains for Self-Supervised Feature Learning},

author = {Siddharth Gururani and Alexander Lerch and Mason Bretan},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/06/Gururani-et-al.-A-Comparison-of-Music-Input-Domains-for-Self-Super.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {ICML Machine Learning for Music Discovery Workshop (ML4MD), Extended Abstract},

address = {Long Beach},

abstract = {In music using neural networks to learn effective feature spaces, or embeddings, that capture useful characteristics has been demonstrated in the symbolic and audio domains. In this work, we compare the symbolic and audio domains, attempting to identify the benefits of each, and whether incorporating both of the representations during learning has utility. We use a self-supervising siamese network to learn a low-dimensional representation of three second music clips and evaluate the learned features on their ability to perform a variety of music tasks. We use a polyphonic piano performance dataset and directly compare the performance on these tasks with embeddings derived from synthesized audio and the corresponding symbolic representations.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{pati_latent_2019,

title = {Latent Space Regularization for Explicit Control of Musical Attributes},

author = {Ashis Pati and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/06/Pati-and-Lerch-Latent-Space-Regularization-for-Explicit-Control-o.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {ICML Machine Learning for Music Discovery Workshop (ML4MD), Extended Abstract},

address = {Long Beach},

abstract = {Deep generative models for music are often restrictive since they do not allow users any meaningful control over the generated music. To address this issue, we propose a novel latent space regularization technique which is capable of structuring the latent space of a deep generative model by encoding musically meaningful attributes along specific dimensions of the latent space. This, in turn, can provide users with explicit control over these attributes during inference and thereby, help design intuitive musical interfaces to enhance creative workflows.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{genchel_explicitly_2019,

title = {Explicitly Conditioned Melody Generation: A Case Study with Interdependent RNNs},

author = {Benjamin Genchel and Ashis K Pati and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/06/Genchel-et-al.-2019-Explicitly-Conditioned-Melody-Generation-A-Case-S.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the International Workshop on Musical Metacreation (MuMe)},

address = {Charlotte},

abstract = {Deep generative models for symbolic music are typically designed to model temporal dependencies in music so as to predict the next musical event given previous events. In many cases, such models are expected to learn abstract concepts such as harmony, meter, and rhythm from raw musical data without any additional information. In this study, we investigate the effects of explicitly conditioning deep generative models with musically relevant information. Specifically, we study the effects of four different conditioning inputs on the performance of a recurrent monophonic melody generation model. Several combinations of these conditioning inputs are used to train different model variants which are then evaluated using three objective evaluation paradigms across two genres of music. The results indicate musically relevant conditioning significantly improves learning and performance, and reveal how this information affects learning of musical features related to pitch and rhythm. An informal subjective evaluation suggests a corresponding improvement in the aesthetic quality of generations.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lerch_music_2019,

title = {Music Performance Analysis: A Survey},

author = {Alexander Lerch and Claire Arthur and Ashis Pati and Siddharth Gururani},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/06/Lerch-et-al.-2019-Music-Performance-Analysis-A-Survey.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

address = {Delft},

abstract = {Music Information Retrieval (MIR) tends to focus on the analysis of audio signals. Often, a single music recording is used as representative of a "song" even though different performances of the same song may reveal different properties. A performance is distinct in many ways from a (arguably more abstract) representation of a "song," "piece," or musical score. The characteristics of the (recorded) performance -as opposed to the score or musical idea- can have a major impact on how a listener perceives music. The analysis of music performance, however, has been traditionally only a peripheral topic for the MIR research community. This paper surveys the field of Music Performance Analysis (MPA) from various perspectives, discusses its significance to the field of MIR, and points out opportunities for future research in this field.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{pati_learning_2019,

title = {Learning to Traverse Latent Spaces for Musical Score Inpainting},

author = {Ashis Pati and Alexander Lerch and Ga\"{e}tan Hadjeres},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/06/Pati-et-al.-2019-Learning-to-Traverse-Latent-Spaces-for-Musical-Sco.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

address = {Delft},

abstract = {Music Inpainting is the task of filling in missing or lost information in a piece of music. We investigate this task from an interactive music creation perspective. To this end, a novel deep learning-based approach for musical score inpainting is proposed. The designed model takes both past and future musical context into account and is capable of suggesting ways to connect them in a musically meaningful manner. To achieve this, we leverage the representational power of the latent space of a Variational Auto-Encoder and train a Recurrent Neural Network which learns to traverse this latent space conditioned on the past and future musical contexts. Consequently, the designed model is capable of generating several measures of music to connect two musical excerpts. The capabilities and performance of the model are showcased by comparison with competitive baselines using several objective and subjective evaluation methods. The results show that the model generates meaningful inpaintings and can be used in interactive music creation applications. Overall, the method demonstrates the merit of learning complex trajectories in the latent spaces of deep generative models.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{huang_automatic_2019,

title = {Automatic Assessment of Sight-Reading Exercises},

author = {Jiawen Huang and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/07/Huang-and-Lerch-2019-Automatic-Assessment-of-Sight-Reading-Exercises.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

address = {Delft},

abstract = {Sight-reading requires a musician to decode, process, and perform a musical score quasi-instantaneously and without rehearsal. Due to the complexity of this task, it is difficult to assess the proficiency of a sight-reading performance, and it is even more challenging to model its human assessment. This study aims at evaluating and identifying effective features for automatic assessment of sight-reading performance. The evaluated set of features comprises task-specific, hand-crafted, and interpretable features designed to represent various aspect of sight-reading performance covering parameters such as intonation, timing, dynamics, and score continuity. The most relevant features are identified by Principal Component Analysis and forward feature selection. For context, the same features are also applied to the assessment of rehearsed student music performances and compared across different assessment categories. The results show potential of automatic assessment models for sight-reading and the relevancy of different features as well as the contribution of different feature groups to different assessment categories.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gururani_attention_2019,

title = {An Attention Mechanism for Music Instrument Recognition},

author = {Siddharth Gururani and Mohit Sharma and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2019/07/Gururani-et-al.-2019-An-Attention-Mechanism-for-Music-Instrument-Recogn.pdf},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

address = {Delft},

abstract = {While the automatic recognition of musical instruments has seen significant progress, the task is still considered hard for music featuring multiple instruments as opposed to single instrument recordings. Datasets for polyphonic instrument recognition can be categorized into roughly two categories. Some, suchasMedleyDB,havestrongper-frameinstrument activity annotations but are usually small in size. Other, larger datasets such as OpenMIC only have weak labels, i.e., instrument presence or absence is annotated only for long snippets of a song. We explore an attention mechanism for handling weakly labeled data for multi-label instrument recognition. Attention has been found to perform well for other tasks with weakly labeled data. We compare the proposed attention model to multiple models which include a baseline binary relevance random forest, recurrent neural network, and fully connected neural networks. Our results show that incorporating attention leads to an overall improvement in classification accuracy metrics across all 20 instruments in the OpenMIC dataset. We find that attention enables models to focus on (or ‘attend to’) specific time segments in the audio relevant to each instrument label leading to interpretable results.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wu_learned_2018,

title = {Learned Features for the Assessment of Percussive Music Performances},

author = {Chih-Wei Wu and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2018/01/Wu_Lerch_2018_Learned-Features-for-the-Assessment-of-Percussive-Music-Performances.pdf},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the International Conference on Semantic Computing (ICSC)},

publisher = {IEEE},

address = {Laguna Hills},

keywords = {audio, feature learning, music performance analysis, percussion},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{xambo_live_2018,

title = {Live Repurposing of Sounds: MIR Explorations with Personal and Crowd-sourced Databases},

author = {Anna Xambo and Gerard Roma and Alexander Lerch and Matthieu Barthet and Gyorgy Fazekas},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2018/04/Xambo-et-al.-2018-Live-Repurposing-of-Sounds-MIR-Explorations-with-.pdf},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the Conference on New Interfaces for Musical Expression (NIME)},

address = {Blacksburg},

abstract = {The recent increase in the accessibility and size of personal and crowd-sourced digital sound collections brought about a valuable resource for music creation. Finding and retrieving relevant sounds in performance leads to challenges that can be approached using music information retrieval (MIR). In this paper, we explore the use of MIR to retrieve and repurpose sounds in musical live coding. We present a live coding system built on SuperCollider enabling the use of audio content from Creative Commons (CC) sound databases such as Freesound or personal sound databases. The novelty of our approach lies in exploiting high-level MIR methods (e.g. query by pitch or rhythmic cues) using live coding techniques applied to sounds. We demonstrate its potential through the reflection of an illustrative case study and the feedback from four expert users. The users tried the system with either a personal database or a crowd-source database and reported its potential in facilitating tailorability of the tool to their own creative workflows. This approach to live repurposing of sounds can be applied to real-time interactive systems for performance and composition beyond live coding, as well as inform live coding and MIR research.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{seipel_multi-track_2018,

title = {Multi-Track Crosstalk Reduction},

author = {Fabian Seipel and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2018/06/Seipel-and-Lerch-2018-Multi-Track-Crosstalk-Reduction.pdf},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the Audio Engineering Society Convention},

publisher = {Audio Engineering Society (AES)},

address = {Milan},

abstract = {While many music-related blind source separation methods focus on mono or stereo material, the detection and reduction of crosstalk in multi-track recordings is less researched. Crosstalk or ’bleed’ of one recorded channel in another is a very common phenomenon in specific genres such as jazz and classical, where all instrumentalists are recorded simultaneously. We present an efficient algorithm that estimates the crosstalk amount in the spectral domain and applies spectral subtraction to remove it. Randomly generated artificial mixtures from various anechoic orchestral source material were employed to develop and evaluate the algorithm, which scores an average SIR-Gain result of 15.14dB on various datasets with different amounts of simulated crosstalk.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gururani_instrument_2018,

title = {Instrument Activity Detection in Polyphonic Music using Deep Neural Networks},

author = {Siddharth Gururani and Cameron Summers and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2018/06/Gururani-et-al.-Instrument-Activity-Detection-in-Polyphonic-Music-.pdf},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

address = {Paris},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wu_labeled_2018,

title = {From Labeled to Unlabeled Data -- On the Data Challenge in Automatic Drum Transcription},

author = {Chih-Wei Wu and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2018/06/Wu-and-Lerch-From-Labeled-to-Unlabeled-Data-On-the-Data-Chal.pdf},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

address = {Paris},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{subramanian_concert_2018,

title = {Concert Stitch: Organization and Synchromization of Crowd-Sourced Recordings},

author = {Vinod Subramanian and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2018/06/Subramanian-and-Lerch-Concert-Stitch-Organization-and-Synchromization-o.pdf},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

address = {Paris},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gururani_analysis_2018,

title = {Analysis of Objective Descriptors for Music Performance Assessment},

author = {Siddharth Gururani and Kumar Ashis Pati and Chih-Wei Wu and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2018/06/Gururani-et-al.-2018-Analysis-of-Objective-Descriptors-for-Music-Perfor.pdf},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the International Conference on Music Perception and Cognition (ICMPC)},

address = {Montreal, Canada},

abstract = {The assessment of musical performances in, e.g., student competitions or auditions, is a largely subjective evaluation of a performer's technical skills and expressivity. Objective descriptors extracted from the audio signal have been proposed for automatic performance assessment in such a context. Such descriptors represent different aspects of pitch, dynamics and timing of a performance and have been shown to be reasonably successful in modeling human assessments of student performances through regression. This study aims to identify the influence of individual descriptors on models of human assessment in 4 categories: musicality, note accuracy, rhythmic accuracy, and tone quality. To evaluate the influence of the individual descriptors, the descriptors highly correlated with the human assessments are identified. Subsequently, various subsets are chosen using different selection criteria and the adjusted R-squared metric is computed to evaluate the degree to which these subsets explain the variance in the assessments. In addition, sequential forward selection is performed to identify the most meaningful descriptors. The goal of this study is to gain insights into which objective descriptors contribute most to the human assessments as well as to identify a subset of well-performing descriptors. The results indicate that a small subset of the designed descriptors can perform at a similar accuracy as the full set of descriptors. Sequential forward selection shows how around 33% of the descriptors do not add new information to the linear regression models, pointing towards redundancy in the descriptors.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{genchel_lead_2018,

title = {Lead Sheet Generation with Musically Interdependent Networks},

author = {Benjamin Genchel and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2018/08/Genchel-and-Lerch-2018-Lead-Sheet-Generation-with-Musically-Interdependen.pdf},

year  = {2018},

date = {2018-01-01},

booktitle = {Late Breaking Abstract, Proceedings of Computer Simulation of Musical Creativity (CSMC)},

address = {Dublin},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wu_blind_2017,

title = {Blind Bandwidth Extension using K-Means and Support Vector Regression},

author = {Chih-Wei Wu and Mark Vinton},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2017/04/Wu-and-Vinton-2017-Blind-Bandwidth-Extension-using-K-Means-and-Suppor.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

publisher = {IEEE},

address = {New Orleans},

abstract = {In this paper, a blind bandwidth extension algorithm for music signals has been proposed. This method applies the K-means algorithm to firstly cluster audio data in the feature space, and constructs multiple envelope predictors for each cluster accordingly using Support Vector Regression (SVR). A set of well-established audio features for Music Information Retrieval (MIR) has been used to characterize the audio content. The resulting system is applied to a variety of music signals without any side information provided. The subjec tive listening test results show that his method can improve the perceptual quality successfully, ut the minor artifacts still leave room for future improvements.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gururani_automatic_2017,

title = {Automatic Sample Detection in Polyphonic Music},

author = {Siddharth Gururani and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2017/07/Gururani_Lerch_2017_Automatic-Sample-Detection-in-Polyphonic-Music.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {International Society for Music Information Retrieval (ISMIR)},

address = {Suzhou},

abstract = {The term `sampling' refers to the usage of snippets or loops from existing songs or sample libraries in new songs, mashups, or other music productions. The ability to automatically detect sampling in music is, for instance, beneficial for studies tracking artist influences geographically and temporally. We present a method based on Non-negative Matrix Factorization (NMF) and Dynamic Time Warping (DTW) for the automatic detection of a sample in a pool of songs. The method comprises of two processing steps: first, the DTW alignment path between NMF activations of a song and query sample is computed. Second, features are extracted from this path and used to train a Random Forest classifier to detect the presence of the sample. The method is able to identify samples that are pitch shifted and/or time stretched with approximately 63% F-measure. We evaluate this method against a new publicly available dataset of real-world sample and song pairs.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gururani_mixing_2017,

title = {Mixing Secrets: A multitrack dataset for instrument detection in polyphonic music},

author = {Siddharth Gururani and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2017/10/Gururani_Lerch_2017_Mixing-Secrets.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Late Breaking Demo (Extended Abstract), Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {International Society for Music Information Retrieval (ISMIR)},

address = {Suzhou},

abstract = {Instrument recognition as a task in MIR is largely data drive. This drives a need for large datasets that cater to the need of these algorithms. Several datasets exist for the task of instrument recognition in monophonic signals. For polyphonic music, creating a finely labeled dataset for instrument recognition is a hard task and using multi-track data eases that process. We present 250+ multi-tracks that have been labeled for instrument recognition and release the annotations to be used in the community. The process of data acquisition, cleaning and labeling has been detailed in this late-breaking demo.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{pati_dataset_2017,

title = {A Dataset and Method for Electric Guitar Solo Detection in Rock Music},

author = {Kumar Ashis Pati and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2017/06/Pati_Lerch_2017_A-Dataset-and-Method-for-Electric-Guitar-Solo-Detection-in-Rock-Music.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the AES Conference on Semantic Audio},

publisher = {Audio Engineering Society (AES)},

address = {Erlangen},

abstract = {This paper explores the problem of automatically detecting electric guitar solos in rock music. A baseline study using standard spectral and temporal audio features in conjunction with an SVM classifier is carried out. To improve detection rates, custom features based on predominant pitch and structural segmentation of songs are designed and investigated. The evaluation of different feature combinations suggests that the combination of all features followed by a post-processing step results in the best accuracy. A macro-accuracy of 78.6% with a solo detection precision of 63.3% is observed for the best feature combination. This publication is accompanied by release of an annotated dataset of electric guitar solos to encourage future research in this area.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{southall_mdb_2017,

title = {MDB Drums --- An Annotated Subset of MedleyDB for Automatic Drum Transcription},

author = {Carl Southall and Chih-Wei Wu and Alexander Lerch and Jason A Hockman},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2017/10/Wu-et-al_2017_MDB-Drums-An-Annotated-Subset-of-MedleyDB-for-Automatic-Drum-Transcription.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Late Breaking Demo (Extended Abstract), Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {International Society for Music Information Retrieval (ISMIR)},

address = {Suzhou},

abstract = {In this paper we present MDB Drums, a new dataset for automatic drum transcription (ADT) tasks. This dataset is built on top of the MusicDelta subset of the MedleyDB dataset, taking advantage of real-world recordings in multi-track format. The dataset is comprised of a variety of genres, providing a balanced pool for developing and evaluating ADT models with respect to various musical styles. 

To reduce the cost of the labor-intensive process of manual annotation, a semi-automatic process was utilised in both the annotation and quality control processes. The pre sented dataset consists of 23 tracks with a total of 7994 onsets. These onsets are divided into 6 classes based on drum instruments or 21 subclasses based on playing techniques. Every track consists of a drum-only track as well 

as multiple accompanied tracks, enabling audio files containing different combinations of instruments to be used in the ADT evaluation process.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{vidwans_objective_2017,

title = {Objective descriptors for the assessment of student music performances},

author = {Amruta Vidwans and Siddharth Gururani and Chih-Wei Wu and Vinod Subramanian and Rupak Vignesh Swaminathan and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2017/06/Vidwans-et-al_2017_Objective-descriptors-for-the-assessment-of-student-music-performances.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the AES Conference on Semantic Audio},

publisher = {Audio Engineering Society (AES)},

address = {Erlangen},

abstract = {Assessment of students’ music performances is a subjective task that requires the judgment of technical correctness as well as aesthetic properties. A computational model automatically evaluating music performance based on objective measurements could ensure consistent and reproducible assessments for, e.g., automatic music tutoring systems. In this study, we investigate the effectiveness of various audio descriptors for assessing performances. Specifically, three different sets of features, including a baseline set, score-independent features, and score-based features, are compared with respect to their efficiency in regression tasks. The results show that human assessments can be modeled to a certain degree, however, the generality of the model still needs further investigation.},

keywords = {computational auditory scene analysis, Computer sound processing, Content analysis (Communication), Data processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wu_automatic_2017,

title = {Automatic drum transcription using the student-teacher learning paradigm with unlabeled music data},

author = {Chih-Wei Wu and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2017/07/Wu_Lerch_2017_Automatic-drum-transcription-using-the-student-teacher-learning-paradigm-with.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {International Society for Music Information Retrieval (ISMIR)},

address = {Suzhou},

abstract = {Automatic drum transcription is a sub-task of automatic music transcription that converts drum-related audio events into musical notation. While noticeable progress has been made in the past by combining pattern recognition methods with audio signal processing techniques, the major limitation of many state-of-the-art systems still originates from the difficulty of obtaining a meaningful amount of annotated data to support the data-driven algorithms. In this work, we address the challenge of insufficiently labeled data by exploring the possibility of utilizing unlabeled music data from online resources. Specifically, a student neural network is trained using the labels generated from multiple teacher systems. The performance of the model is evaluated on a publicly available dataset. The results show the general viability of using unlabeled music data to improve the performance of drum transcription systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhiqian_chen_learning_2017,

title = {Learning to Fuse Music Genres with Generative Adversarial Dual Learning},

author = {Zhiqian Chen and Chih-Wei Wu and Yen-Cheng Lu and Alexander Lerch and Chang-Tien Lu},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2017/11/Zhiqian-Chen-et-al_2017_Learning-to-Fuse-Music-Genres-with-Generative-Adversarial-Dual-Learning.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the International Conference on Data Mining (ICDM)},

publisher = {Institute of Electrical and Electronics Engineers (IEEE)},

address = {New Orleans},

abstract = {FusionGAN is a novel genre fusion framework for music generation that integrates the strengths of generative adversarial networks and dual learning. In particular, the proposed method offers a dual learning extension that can effectively integrate the styles of the given domains. To efficiently quantify the difference among diverse domains and avoid the vanishing gradient issue, FusionGAN provides a Wasserstein based metric to approximate the distance between the target domain and the existing domains. Adopting the Wasserstein distance, a new domain is created by combining the patterns of the existing domains using adversarial learning. Experimental results on public music datasets demonstrated that our approach could effectively merge two genres.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{laguna_efficient_2016,

title = {An Efficient Algorithm For Clipping Detection And Declipping Audio},

author = {Christopher Laguna and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/09/Laguna_Lerch_2016_An-Efficient-Algorithm-For-Clipping-Detection-And-Declipping-Audio.pdf},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of the 141st AES Convention},

publisher = {Audio Engineering Society (AES)},

address = {Los Angeles},

abstract = {We present an algorithm for end to end declipping, which includes clipping detection and the replacement 

of clipped samples. To detect regions of clipping, we analyze the signal’s amplitude histogram and the 

shape of the signal in the time-domain. The sample replacement algorithm uses a two-pass approach: short 

regions of clipping are replaced in the time-domain and long regions of clipping are replaced in the 

frequency-domain. The algorithm is robust against different types of clipping and is efficient compared to 

existing approaches. The algorithm has been implemented in an open source JavaScript client-side web 

application. Clipping detection is shown to give an f-measure of 0.92 and is robust to the clipping level.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lu_unsupervised_2016,

title = {An Unsupervised Approach to Anomaly Detection in Music Datasets},

author = {Yen-Cheng Lu and Chih-Wei Wu and Chang-Tien Lu and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/07/Lu-et-al_2016_An-Unsupervised-Approach-to-Anomaly-Detection-in-Music-Datasets.pdf},

doi = {10.1145/2911451.2914700},

isbn = {978-1-4503-4069-4},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of the ACM SIGIR Conference (SIGIR)},

pages = {749--752},

publisher = {ACM},

address = {Pisa},

series = {SIGIR '16},

abstract = {This paper presents an unsupervised method for systematically identifying anomalies in music datasets. The model integrates categorical regression and robust estimation techniques to infer anomalous scores in music clips. When applied to a music genre recognition dataset, the new method is able to detect corrupted, distorted, or mislabeled audio samples based on commonly used features in music information retrieval. The evaluation results show that the algorithm outperforms other anomaly detection methods and is capable of finding problematic samples identified by human experts. The proposed method introduces a preliminary framework for anomaly detection in music data that can serve as a useful tool to improve data integrity in the future.},

keywords = {anomaly detection, data clean-up, music genre retrieval, music information retrieval},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lu_automatic_2016,

title = {Automatic Outlier Detection in Music Genre Datasets},

author = {Yen-Cheng Lu and Chih-Wei Wu and Chang-Tien Lu and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/07/Lu-et-al_2016_Automatic-Outlier-Detection-in-Music-Genre-Datasets.pdf},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {ISMIR},

address = {New York},

series = {ISMIR},

abstract = {Outlier detection, also known as anomaly detection, is an 

importanttopicthathasbeenstudiedfordecades. Anoutlier 

detection system is able to identify anomalies in a dataset 

and thus improve data integrity by removing the detected 

outliers. It has been successfully applied to different types 

of data in various fields such as cyber-security, finance, 

and transportation. In the field of Music Information Re- 

trieval (MIR), however, the number of related studies is 

small. In this paper, we introduce different state-of-the-art 

outlier detection techniques and evaluate their viability in 

the context of music datasets. More specifically, we present 

a comparative study of 6 outlier detection algorithms ap- 

plied to a Music Genre Recognition (MGR) dataset. It is 

determined how well algorithms can identify mislabeled or 

corrupted files, and how much the quality of the dataset can 

be improved. Results indicate that state-of-the-art anomaly 

detection systems have problems identifying anomalies in 

MGR datasets reliably.},

keywords = {anomaly detection, data clean-up, music genre retrieval, music information retrieval},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{winters_automatic_2016,

title = {Automatic Practice Logging: Introduction, Dataset \& Preliminary Study},

author = {Michael R Winters and Siddharth Gururani and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/07/Winters-et-al_2016_Automatic-Practice-Logging.pdf},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {ISMIR},

address = {New York},

abstract = {Musicians spend countless hours practicing their instru- 

ments. To document and organize this time, musicians com- 

monly use practice charts to log their practice. However, 

manual techniques require time, dedication, and experience 

to master, are prone to fallacy and omission, and ultimately 

can not describe the subtle variations in each repetition. 

This paper presents an alternative: by analyzing and clas- 

sifying the audio recorded while practicing, logging could 

occur automatically, with levels of detail, accuracy, and ease 

that would not be possible otherwise. Towards this goal, 

we introduce the problem of Automatic Practice Logging 

(APL), including a discussion of the benefits and unique 

challenges it raises. We then describe a new dataset of over 

600 annotated recordings of solo piano practice, which can 

be used to design and evaluate APL systems. After fram- 

ing our approach to the problem, we present an algorithm 

designed to align short segments of practice audio with 

reference recordings using pitch chroma and dynamic time 

warping.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wu_towards_2016,

title = {Towards the Objective Assessment of Music Performances},

author = {Chih-Wei Wu and Siddharth Gururani and Christopher Laguna and Ashis Pati and Amruta Vidwans and Alexander Lerch},

url = {http://www.icmpc.org/icmpc14/proceedings.html},

isbn = {1-879346-65-5},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of the International Conference on Music Perception and Cognition (ICMPC)},

pages = {99--103},

address = {San Francisco},

abstract = {The qualitative assessment of music performances is a task that is 

influenced by technical correctness, deviations from established 

performance standards, and aesthetic judgment. Despite its inherently 

subjective nature, a quantitative overall assessment is often desired, 

as exemplified by US all-state auditions or other competitions. A 

model that automatically generates assessments from the audio data 

would allow for objective assessments and enable musically 

intelligent computer-assisted practice sessions for students learning 

an instrument. While existing systems are already able to provide 

similar basic functionality, they rely on the musical score as prior 

knowledge. In this paper, we present a score-independent system for 

assessing student instrument performances based on audio recordings. 

This system aims to characterize the performance with both 

well-established and custom-designed audio features, model expert 

assessments of student performances, and predict the assessment of 

unknown audio recordings. The results imply the viability of 

modeling human assessment with score-independent audio features. 

Results could lead towards more general software music tutoring 

systems that do not require score information for the assessment of 

student music performances.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wu_drum_2016,

title = {On Drum Playing Technique Detection in Polyphonic Mixtures},

author = {Chih-Wei Wu and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/07/Wu_Lerch_2016_On-Drum-Playing-Technique-Detection-in-Polyphonic-Mixtures.pdf},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {ISMIR},

address = {New York},

abstract = {In this paper, the problem of drum playing technique 

detection in polyphonic mixtures of music is addressed. 

We focus on the identification of 4 rudimentary techniques: 

strike, buzz roll, flam, and drag. The specifics and the 

challenges of this task are being discussed, and different 

sets of features are compared, including various features 

extracted from NMF-based activation functions, as well 

as baseline spectral features. We investigate the capabil- 

ities and limitations of the presented system in the case 

of real-world recordings and polyphonic mixtures. To de- 

sign and evaluate the system, two datasets are introduced: a 

training dataset generated from individual drum hits, and ad- 

ditional annotations of the well-known ENST drum dataset 

minus one subset as test dataset. The results demonstrate 

issues with the traditionally used spectral features, and in- 

dicate the potential of using NMF activation functions for 

playing technique detection, however, the performance of 

polyphonic music still leaves room for future improvement.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{xambo_learning_2016,

title = {Learning to code through MIR},

author = {Anna Xambo and Alexander Lerch and Jason Freeman},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/08/Xambo-et-al.-2016-Learning-to-code-through-MIR.pdf},

year  = {2016},

date = {2016-01-01},

booktitle = {Late Breaking Demo (Extended Abstract), Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)},

publisher = {ISMIR},

address = {New York},

abstract = {An approach to teaching computer science (CS) in high- 

schools is using EarSketch, a free online tool for teaching 

CS concepts while making music. In this demonstration we 

present the potential of teaching music information retrieval 

(MIR) concepts using EarSketch. The aim is twofold: to 

discuss the benefits of introducing MIR concepts in the 

classroom and to shed light on how MIR concepts can 

be gently introduced in a CS curriculum. We conclude by 

identifying the advantagesofteachingMIR inthe classroom 

and pointing to future directions for research.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gupta_perceptual_2015,

title = {On the Perceptual Relevance of Objective Source Separation Measures for Singing Voice Separation},

author = {Udit Gupta and Elliot Moore II and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/10/Gupta-et-al_2015_On-the-Perceptual-Relevance-of-Objective-Source-Separation-Measures-for-Singing.pdf},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},

publisher = {IEEE},

address = {New Paltz},

abstract = {Singing Voice Separation (SVS) is a task which uses audio source 

separation methods to isolate the vocal component from the back- 

ground accompaniment for a song mix. This paper discusses the 

methods of evaluating SVS algorithms, and determines how the 

current state of the art measures correlate to human perception. A 

modified ITU-R BS.1543 MUSHRA test is used to get the human 

perceptual ratings for the outputs of various SVS algorithms, which 

are correlated with widely used objective measures for source sep- 

aration quality. The results show that while the objective measures 

provide a moderate correlation with perceived intelligibility and 

isolation, they may not adequately assess the overall perceptual 

quality.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lykartsis_analysis_2015,

title = {Analysis of Speech Rhythm for Language Identification Based on Beat Histograms},

author = {Athanasios Lykartsis and Alexander Lerch and Stefan Weinzierl},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/06/Lykartsis%20et%20al_2015_Analysis%20of%20Speech%20Rhythm%20for%20Language%20Identification%20Based%20on%20Beat%20Histograms.pdf},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the DAGA (Jahrestagung fur Akustik)},

address = {Nuremberg},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}