publications

@inproceedings{ding_embedding_2024,

title = {Embedding Compression for Teacher-to-Student Knowledge Transfer},

author = {Yiwei Ding and Alexander Lerch},

url = {http://arxiv.org/abs/2402.06761},

doi = {10.48550/arXiv.2402.06761},

year  = {2024},

date = {2024-02-01},

urldate = {2024-02-27},

booktitle = {Proceedings of the International Conference on Acoustics Speech and Signal Processing (ICASSP) - Satellite Workshop Deep Neural Network Model Compression},

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

address = {Seoul, Korea},

abstract = {Common knowledge distillation methods require the teacher model and the student model to be trained on the same task. However, the usage of embeddings as teachers has also been proposed for different source tasks and target tasks. Prior work that uses embeddings as teachers ignores the fact that the teacher embeddings are likely to contain irrelevant knowledge for the target task. To address this problem, we propose to use an embedding compression module with a trainable teacher transformation to obtain a compact teacher embedding. Results show that adding the embedding compression module improves the classification performance, especially for unsupervised teacher embeddings. Moreover, student models trained with the guidance of embeddings show stronger generalizability.},

note = {arXiv:2402.06761 [cs]},

keywords = {Computer Science - Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{seshadri_asped_2024,

title = {ASPED: An Audio Dataset for Detecting Pedestrians},

author = {Pavan Seshadri and Chaeyeon Han and Bon-Woo Koo and Noah Posner and Subhrajit Guhathakurta and Alexander Lerch},

url = {http://arxiv.org/abs/2309.06531},

doi = {10.48550/arXiv.2309.06531},

year  = {2024},

date = {2024-01-01},

urldate = {2023-12-14},

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

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

address = {Seoul},

abstract = {We introduce the new audio analysis task of pedestrian detection and present a new large-scale dataset for this task. While the preliminary results prove the viability of using audio approaches for pedestrian detection, they also show that this challenging task cannot be easily solved with standard approaches.},

keywords = {Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{watcharasupat_quantifying_2024,

title = {Quantifying Spatial Audio Quality Impairment},

author = {Karn N Watcharasupat and Alexander Lerch},

url = {http://arxiv.org/abs/2309.06531},

doi = {10.48550/arXiv.2309.06531},

year  = {2024},

date = {2024-01-01},

urldate = {2023-12-14},

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

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

address = {Seoul},

keywords = {Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ding_audio_2023,

title = {Audio Embeddings as Teachers for Music Classification},

author = {Yiwei Ding and Alexander Lerch},

url = {http://arxiv.org/abs/2306.17424},

doi = {10.48550/arXiv.2306.17424},

year  = {2023},

date = {2023-06-01},

urldate = {2023-06-01},

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

address = {Milan, Italy},

abstract = {Music classification has been one of the most popular tasks in the field of music information retrieval. With the development of deep learning models, the last decade has seen impressive improvements in a wide range of classification tasks. However, the increasing model complexity makes both training and inference computationally expensive. In this paper, we integrate the ideas of transfer learning and feature-based knowledge distillation and systematically investigate using pre-trained audio embeddings as teachers to guide the training of low-complexity student networks. By regularizing the feature space of the student networks with the pre-trained embeddings, the knowledge in the teacher embeddings can be transferred to the students. We use various pre-trained audio embeddings and test the effectiveness of the method on the tasks of musical instrument classification and music auto-tagging. Results show that our method significantly improves the results in comparison to the identical model trained without the teacher's knowledge. This technique can also be combined with classical knowledge distillation approaches to further improve the model's performance.},

keywords = {Computer Science - Information Retrieval, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{knees_milc_2023,

title = {MILC 2023: 3rd Workshop on Intelligent Music Interfaces for Listening and Creation},

author = {Peter Knees and Alexander Lerch},

url = {https://dl.acm.org/doi/10.1145/3581754.3584164},

doi = {10.1145/3581754.3584164},

isbn = {9798400701078},

year  = {2023},

date = {2023-03-01},

urldate = {2023-03-31},

booktitle = {Companion Proceedings of the 28th International Conference on Intelligent User Interfaces},

pages = {185--186},

publisher = {Association for Computing Machinery},

address = {Sydney},

series = {IUI '23 Companion},

abstract = {The third edition of the Workshop on Intelligent Music Interfaces for Listening and Creation (MILC), held in collaboration with the 28th International Conference on Intelligent User Interfaces (IUI) features a half-day program addressing recent and future developments in human-centered music technology. The presented papers cover recommendation in sound libraries, the use of generative systems for composition in Digital Audio Workstations (DAWs), tools for richer means of interaction with music streaming platforms, and music personalization for Cochlear implant users.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chen_music_2023,

title = {Music Instrument Classification Reprogrammed},

author = {Hsin-Hung Chen and Alexander Lerch},

url = {https://arxiv.org/abs/2211.08379},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the International Conference on Multimedia Modeling (MMM)},

address = {Bergen, Norway},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{smith_impact_2023,

title = {The Impact of Salient Musical Features in a Hybrid Recommendation System for a Sound Library},

author = {Jason Brent Smith and Ashvala Vinay and Jason Freeman},

url = {https://ceur-ws.org/Vol-3359/paper18.pdf},

year  = {2023},

date = {2023-01-01},

booktitle = {Joint Proceedings of the ACM IUI Workshops (MILC)},

address = {Sydney},

abstract = {EarSketch is an online learning environment that teaches coding and music concepts through the computational manipulation of sounds selected from a large sound library. It features sound recommendations based on acoustic similarity and co-usage with a user’s current sound selection in order to encourage exploration of the library. However, students have reported that the recommended sounds do not complement their current projects in terms of two areas: musical key and rhythm. We aim to improve the relevance of these recommendations through the inclusion of these two musically related features. This paper describes the addition of key signature and beat extraction to the EarSketch sound recommendation model in order to improve the musical compatibility of the recommendations with the sounds in a user’s project. Additionally, we present an analysis of the effects of these new recommendation strategies on user exploration and usage of the recommended sounds. The results of this analysis suggest that the addition of explicitly musically-relevant attributes increases the coverage of the sound library among sound recommendations as well as the sounds selected by users. It reflects the importance of including multiple musical attributes when building recommendation systems for creative and open-ended musical systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hung_low-resource_2023,

title = {Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming},

author = {Yun-Ning Hung and Chao-Han Huck Yang and Pin-Yu Chen and Alexander Lerch},

url = {https://arxiv.org/abs/2211.01317},

doi = {10.1109/ICASSP49357.2023.10096568},

year  = {2023},

date = {2023-01-01},

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

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

address = {Rhodes Island, Greece},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{vinay_aquatk_2023,

title = {AQUATK: An Audio Quality Assessment Toolkit},

author = {Ashvala Vinay and Alexander Lerch},

url = {https://arxiv.org/abs/2311.10113},

doi = {10.48550/arXiv.2311.10113},

year  = {2023},

date = {2023-01-01},

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 = {Milan},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Lam2023PreliminaryInvestigationShortterm,

title = {Preliminary Investigation of the Short-Term in Situ Performance of an 

 Automatic Masker Selection System},

author = {Bhan Lam and Kenneth Ooi and Zhen-Ting Ong and Trevor Wong and Woon-Seng Gan and Karn Watcharasupat},

doi = {10.3397/in_2023_0805},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 52nd International Congress and Exposition on Noise 

 Control Engineering},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Ong2023EffectMaskerSelection,

title = {Effect of Masker Selection Schemes on the Perceived Affective Quality of 

 Soundscapes: A Pilot Study},

author = {Zhen-Ting Ong and Kenneth Ooi and Trevor Wong and Bhan Lam and Woon-Seng Gan and Karn N. Watcharasupat},

doi = {10.3397/in_2023_0791},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 52nd International Congress and Exposition on Noise 

 Control Engineering},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Ooi2023ARAUSv2ExpandedDataset,

title = {ARAUSv2: An Expanded Dataset and Multimodal Models of Affective Responses to 

 Augmented Urban Soundscapes},

author = {Kenneth Ooi and Zhen-Ting Ong and Bhan Lam and Trevor Wong and Woon-Seng Gan and Karn Watcharasupat},

doi = {10.3397/in_2023_0459},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 52nd International Congress and Exposition on Noise 

 Control Engineering},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Ooi2023AutonomousSoundscapeAugmentation,

title = {Autonomous Soundscape Augmentation with Multimodal Fusion of Visual and 

 Participant-linked Inputs},

author = {Kenneth Ooi and Karn N Watcharasupat and Bhan Lam and Zhen-Ting Ong and Woon-Seng Gan},

doi = {10.1109/ICASSP49357.2023.10094866},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 2023 International Conference on Acoustics, Speech, and 

 Signal Processing},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ma_representation_2022,

title = {Representation Learning for the Automatic Indexing of Sound Effects Libraries},

author = {Alison B Ma and Alexander Lerch},

url = {http://arxiv.org/abs/2208.09096},

doi = {10.48550/arXiv.2208.09096},

year  = {2022},

date = {2022-08-01},

urldate = {2022-08-22},

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

address = {Bangalore, IN},

abstract = {Labeling and maintaining a commercial sound effects library is a time-consuming task exacerbated by databases that continually grow in size and undergo taxonomy updates. Moreover, sound search and taxonomy creation are complicated by non-uniform metadata, an unrelenting problem even with the introduction of a new industry standard, the Universal Category System. To address these problems and overcome dataset-dependent limitations that inhibit the successful training of deep learning models, we pursue representation learning to train generalized embeddings that can be used for a wide variety of sound effects libraries and are a taxonomy-agnostic representation of sound. We show that a task-specific but dataset-independent representation can successfully address data issues such as class imbalance, inconsistent class labels, and insufficient dataset size, outperforming established representations such as OpenL3. Detailed experimental results show the impact of metric learning approaches and different cross-dataset training methods on representational effectiveness.},

note = {arXiv:2208.09096 [cs, eess]},

keywords = {Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{vinay_evaluating_2022,

title = {Evaluating Generative Audio Systems and their Metrics},

author = {Ashvala Vinay and Alexander Lerch},

url = {http://arxiv.org/abs/2209.00130},

doi = {10.48550/arXiv.2209.00130},

year  = {2022},

date = {2022-08-01},

urldate = {2022-09-03},

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

address = {Bangalore, IN},

abstract = {Recent years have seen considerable advances in audio synthesis with deep generative models. However, the state-of-the-art is very difficult to quantify; different studies often use different evaluation methodologies and different metrics when reporting results, making a direct comparison to other systems difficult if not impossible. Furthermore, the perceptual relevance and meaning of the reported metrics in most cases unknown, prohibiting any conclusive insights with respect to practical usability and audio quality. This paper presents a study that investigates state-of-the-art approaches side-by-side with (i) a set of previously proposed objective metrics for audio reconstruction, and with (ii) a listening study. The results indicate that currently used objective metrics are insufficient to describe the perceptual quality of current systems.},

note = {arXiv:2209.00130 [cs, eess]},

keywords = {Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wang_catch_2022,

title = {To Catch A Chorus, Verse, Intro, or Anything Else: Analyzing a Song with Structural Functions},

author = {Ju-Chiang Wang and Yun-Ning Hung and Jordan B. L. Smith},

url = {https://ieeexplore.ieee.org/abstract/document/9747252/authors#authors},

doi = {10.1109/ICASSP43922.2022.9747252},

year  = {2022},

date = {2022-05-01},

urldate = {2024-02-08},

booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {416\textendash420},

abstract = {Conventional music structure analysis algorithms aim to divide a song into segments and to group them with abstract labels (e.g., ‘A’, ‘B’, and ‘C’). However, explicitly identifying the function of each segment (e.g., ‘verse’ or ‘chorus’) is rarely attempted, but has many applications. We introduce a multi-task deep learning framework to model these structural semantic labels directly from audio by estimating "verseness," "chorusness," and so forth, as a function of time. We propose a 7-class taxonomy (i.e., intro, verse, chorus, bridge, outro, instrumental, and silence) and provide rules to consolidate annotations from four disparate datasets. We also propose to use a spectral-temporal Transformer-based model, called SpecTNT, which can be trained with an additional connectionist temporal localization (CTL) loss. In cross-dataset evaluations using four public datasets, we demonstrate the effectiveness of the SpecTNT model and CTL loss, and obtain strong results overall: the proposed system outperforms state-of-the-art chorus-detection and boundary-detection methods at detecting choruses and boundaries, respectively.},

note = {ISSN: 2379-190X},

keywords = {Location awareness, music, Music structure, segmentation, semantic labeling, Semantics, Signal processing, Signal processing algorithms, SpecTNT, Taxonomy, Transformer, Transformers},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kalbag_scream_2022,

title = {Scream Detection in Heavy Metal Music},

author = {Vedant Kalbag and Alexander Lerch},

url = {http://arxiv.org/abs/2205.05580},

doi = {10.48550/arXiv.2205.05580},

year  = {2022},

date = {2022-01-01},

booktitle = {Proceedings of the Sound and Music Computing Conference (SMC)},

address = {Saint-Etienne},

abstract = {Harsh vocal effects such as screams or growls are far more common in heavy metal vocals than the traditionally sung vocal. This paper explores the problem of detection and classification of extreme vocal techniques in heavy metal music, specifically the identification of different scream techniques. We investigate the suitability of various feature representations, including cepstral, spectral, and temporal features as input representations for classification. The main contributions of this work are (i) a manually annotated dataset comprised of over 280 minutes of heavy metal songs of various genres with a statistical analysis of occurrences of different extreme vocal techniques in heavy metal music, and (ii) a systematic study of different input feature representations for the classification of heavy metal vocals},

keywords = {Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hung_feature-informed_2022,

title = {Feature-informed Embedding Space Regularization for Audio Classification},

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

url = {http://arxiv.org/abs/2206.04850},

doi = {10.48550/arXiv.2206.04850},

year  = {2022},

date = {2022-01-01},

booktitle = {Proceedings of the European Signal Processing Conference (EUSIPCO)},

address = {Belgrade, Serbia},

abstract = {Feature representations derived from models pre-trained on large-scale datasets have shown their generalizability on a variety of audio analysis tasks. Despite this generalizability, however, task-specific features can outperform if sufficient training data is available, as specific task-relevant properties can be learned. Furthermore, the complex pre-trained models bring considerable computational burdens during inference. We propose to leverage both detailed task-specific features from spectrogram input and generic pre-trained features by introducing two regularization methods that integrate the information of both feature classes. The workload is kept low during inference as the pre-trained features are only necessary for training. In experiments with the pre-trained features VGGish, OpenL3, and a combination of both, we show that the proposed methods not only outperform baseline methods, but also can improve state-of-the-art models on several audio classification tasks. The results also suggest that using the mixture of features performs better than using individual features.},

keywords = {Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{watcharasupat_evaluation_2021,

title = {Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes},

author = {Karn N Watcharasupat and Alexander Lerch},

url = {http://arxiv.org/abs/2110.05587},

year  = {2021},

date = {2021-10-01},

urldate = {2021-11-11},

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

address = {Online},

abstract = {Controllable music generation with deep generative models has become increasingly reliant on disentanglement learning techniques. However, current disentanglement metrics, such as mutual information gap (MIG), are often inadequate and misleading when used for evaluating latent representations in the presence of interdependent semantic attributes often encountered in real-world music datasets. In this work, we propose a dependency-aware information metric as a drop-in replacement for MIG that accounts for the inherent relationship between semantic attributes.},

keywords = {Computer Science - Information Retrieval, Computer Science - Information Theory, Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hung_transcription_2021,

title = {Transcription Is All You Need: Learning To Separate Musical Mixtures With Score As Supervision},

author = {Yun-Ning Hung and Gordon Wichern and Jonathan Le Roux},

url = {https://ieeexplore.ieee.org/abstract/document/9413358/authors#authors},

doi = {10.1109/ICASSP39728.2021.9413358},

year  = {2021},

date = {2021-06-01},

urldate = {2024-02-08},

booktitle = {ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {46\textendash50},

abstract = {Most music source separation systems require large collections of isolated sources for training, which can be difficult to obtain. In this work, we use musical scores, which are comparatively easy to obtain, as a weak label for training a source separation system. In contrast with previous score-informed separation approaches, our system does not require isolated sources, and score is used only as a training target, not required for inference. Our model consists of a separator that outputs a time-frequency mask for each instrument, and a transcriptor that acts as a critic, providing both temporal and frequency supervision to guide the learning of the separator. A harmonic mask constraint is introduced as another way of leveraging score information during training, and we propose two novel adversarial losses for additional fine-tuning of both the transcriptor and the separator. Results demonstrate that using score information outper-forms temporal weak-labels, and adversarial structures lead to further improvements in both separation and transcription performance.},

note = {ISSN: 2379-190X},

keywords = {audio source separation, Conferences, Instruments, music, music transcription, Particle separators, Source separation, Time-frequency analysis, Training, weakly-labeled data, weakly-supervised separation},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{vinay_mind_2021,

title = {Mind the Beat: Detecting Audio Onsets from EEG Recordings of Music Listening},

author = {Ashvala Vinay and Alexander Lerch and Grace Leslie},

url = {https://arxiv.org/abs/2102.06393},

year  = {2021},

date = {2021-01-01},

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

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

address = {Toronto, Ontario, Canada},

abstract = {We propose a deep learning approach to predicting audio event onsets in electroencephalogram (EEG) recorded from users as they listen to music. We use a publicly available dataset containing ten contemporary songs and concurrently recorded EEG. We generate a sequence of onset labels for the songs in our dataset and trained neural networks (a fully connected network (FCN) and a recurrent neural network (RNN)) to parse one second windows of input EEG to predict one second windows of onsets in the audio. We compare our RNN network to both the standard spectral-flux based novelty function and the FCN. We find that our RNN was able to produce results that reflected its ability to generalize better than the other methods. 

 

Since there are no pre-existing works on this topic, the numbers presented in this paper may serve as useful benchmarks for future approaches to this research problem.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{seshadri_improving_2021,

title = {Improving Music Performance Assessment with Contrastive Learning},

author = {Pavan Seshadri and Alexander Lerch},

url = {https://arxiv.org/abs/2108.01711},

year  = {2021},

date = {2021-01-01},

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

pages = {8},

address = {Online},

abstract = {Several automatic approaches for objective music performance assessment (MPA) have been proposed in the past, however, existing systems are not yet capable of reliably predicting ratings with the same accuracy as professional judges. This study investigates contrastive learning as a potential method to improve existing MPA systems. Contrastive learning is a widely used technique in representation learning to learn a structured latent space capable of separately clustering multiple classes. It has been shown to produce state of the art results for image-based classification problems. We introduce a weighted contrastive loss suitable for regression tasks applied to a convolutional neural network and show that contrastive loss results in performance gains in regression tasks for MPA. Our results show that contrastive-based methods are able to match and exceed SoTA performance for MPA regression tasks by creating better class clusters within the latent space of the neural networks.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{pati_is_2021,

title = {Is Disentanglement Enough? On Latent Representations for Controllable Music Generation},

author = {Ashis Pati and Alexander Lerch},

url = {https://arxiv.org/abs/2108.01450},

year  = {2021},

date = {2021-01-01},

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

pages = {8},

address = {Online},

abstract = {Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music. Recent attempts in this direction have relied on learning disentangled representations from data such that the underlying factors of variation are well separated. In this paper, we focus on the relationship between disentanglement and controllability by conducting a systematic study using different supervised disentanglement learning algorithms based on the Variational Auto-Encoder (VAE) architecture. Our experiments show that a high degree of disentanglement can be achieved by using different forms of supervision to train a strong discriminative encoder. However, in the absence of a strong generative decoder, disentanglement does not necessarily imply controllability. The structure of the latent space with respect to the VAE-decoder plays an important role in boosting the ability of a generative model to manipulate different attributes. To this end, we also propose methods and metrics to help evaluate the quality of a latent space with respect to the afforded degree of controllability.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gururani_semi-supervised_2021,

title = {Semi-Supervised Audio Classification with Partially Labeled Data},

author = {Siddharth Gururani and Alexander Lerch},

url = {https://arxiv.org/abs/2111.12761},

year  = {2021},

date = {2021-01-01},

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

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

address = {online},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hung_avaspeech-smad_2021,

title = {AVASPEECH-SMAD: A Strongly Labelled Speech and Music Activity Detection Dataset with Label Co-occurence},

author = {Yun-Ning Hung and Karn N Watcharasupat and Chih-Wei Wu and Iroro Orife and Kelian Li and Pavan Seshadri and Junyoung Lee},

year  = {2021},

date = {2021-01-01},

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

pages = {3},

address = {Online},

abstract = {We propose a dataset, AVASpeech-SMAD, to assist speech and music activity detection research. With frame-level music labels, the proposed dataset extends the existing AVASpeech dataset, which originally consists of 45 hours of audio and speech activity labels. To the best of our knowledge, the proposed AVASpeech-SMAD is the first open-source dataset that features strong polyphonic labels for both music and speech. The dataset was manually annotated and verified via an iterative cross-checking process. A simple automatic examination was also implemented to further improve the quality of the labels. Evaluation results from two state-of-the-art SMAD systems are also provided as a benchmark for future reference.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{huang_score-informed_2020,

title = {Score-informed Networks for Music Performance Assessment},

author = {Jiawen Huang and Yun-Ning Hung and Ashis K Pati and Siddharth Gururani and Alexander Lerch},

url = {https://musicinformatics.gatech.edu/wp-content_nondefault/uploads/2020/08/Huang-et-al.-2020-Score-informed-Networks-for-Music-Performance-Asse.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{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}

}