publications

@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}

}

@inproceedings{lykartsis_beat_2015,

title = {Beat Histogram Features for Rythm-based Musical Genre Classification Using Multiple Novelty Functions},

author = {Athanasios Lykartsis and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/12/DAFx-15_submission_42-1.pdf},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the International Conference on Digital Audio Effects (DAFX)},

address = {Trondheim, Norway},

abstract = {In this paper we present beat histogram features for multiple level 

rhythmdescriptionandevaluatetheminamusicalgenreclassifica- 

tion task. Audio features pertaining to various musical content cat- 

egories and their related novelty functions are extracted as a basis 

for the creation of beat histograms. The proposed features capture 

not only amplitude, but also tonal and general spectral changes 

in the signal, aiming to represent as much rhythmic information 

as possible. The most and least informative features are identi- 

fied through feature selection methods and are then tested using 

Support Vector Machines on five genre datasets concerning classi- 

fication accuracy against a baseline feature set. Results show that 

the presented features provide comparable classification accuracy 

with respect to other genre classification approaches using period- 

icity histograms and display a performance close to that of much 

more elaborate up-to-date approaches for rhythm description. The 

use of bar boundary annotations for the texture frames has pro- 

vided an improvement for the dance-oriented Ballroom dataset. 

The comparably small number of descriptors and the possibility of 

evaluating the influence of specific signal components to the gen- 

eral rhythmic content encourage the further use of the method in 

rhythm description tasks.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lykartsis_beat_2015-1,

title = {Beat Histogram Features from NMF-Based Novelty Functions for Music Classification},

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

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/10/Lykartsis-et-al_2015_Beat-Histogram-Features-from-NMF-Based-Novelty-Functions-for-Music.pdf},

year  = {2015},

date = {2015-01-01},

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

publisher = {ISMIR},

address = {Malaga},

abstract = {In this paper we present novel rhythm features derived from 

drum tracks extracted from polyphonic music and evaluate 

them in a genre classification task. Musical excerpts are 

analyzed using an optimized, partially fixed Non-Negative 

Matrix Factorization (NMF) method and beat histogram 

features are calculated on basis of the resulting activation 

functions for each one out of three drum tracks extracted 

(Hi-Hat, SnareDrumandBassDrum). Thefeaturesareeval- 

uated on two widely used genre datasets (GTZAN and Ball- 

room) using standard classification methods, concerning 

the achieved overall classification accuracy. Furthermore, 

their suitability in distinguishing between rhythmically sim- 

ilar genres and the performance of the features resulting 

from individual activation functions is discussed. Results 

show that the presented NMF-based beat histogram features 

can provide comparable performance to other classification 

systems, while considering strictly drum patterns.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{obrien_genre-specific_2015,

title = {Genre-Specific Key Profiles},

author = {Cian O'Brien and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/09/O'Brien_Lerch_2015_Genre-Specific%20Key%20Profiles.pdf},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the International Computer Music Conference (ICMC)},

publisher = {ICMA},

address = {Denton},

abstract = {The most common approaches to the automatic recognition 

of musical key are template-based, i.e., an extracted pitch 

chroma vector is compared to a template key profile in order 

to identify the most similar key. General as well as domain- 

specific templates have been used in the past, but to the au- 

thors best knowledge there has been no study that evaluated 

genre-specific key profiles extracted from the audio signal. We 

investigate the pitch chroma distributions for 9 different gen- 

res, their distances, and the degree to which these genres can 

be identified using these distributions when utilizing different 

strategies for achieving key-invariance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wu_drum_2015,

title = {Drum Transcription using Partially Fixed Non-Negative Matrix Factorization},

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

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/09/Wu_Lerch_2015_Drum%20Transcription%20using%20Partially%20Fixed%20Non-Negative%20Matrix%20Factorization.pdf},

year  = {2015},

date = {2015-01-01},

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

publisher = {EURASIP},

address = {Nice},

abstract = {In this paper, a drum transcription algorithm using partially 

fixed non-negative matrix factorization is presented. The pro- 

posed method allows users to identify percussive events in 

complex mixtures with a minimal training set. The algorithm 

decomposes the music signal into two parts: percussive part 

with pre-defined drum templates and harmonic part with un- 

defined entries. The harmonic part is able to adapt to the 

music content, allowing the algorithm to work in polyphonic 

mixtures. Drum event times can be simply picked from the 

percussive activation matrix with onset detection. The system 

is efficient and robust even with a minimal training set. The 

recognition rates for the ENST dataset vary from 56.7 to 78.9% 

for three percussive instruments extracted from polyphonic 

music.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wu_drum_2015-1,

title = {Drum Transcription using Partially Fixed Non-Negative Matrix Factorization With Template Adaptation},

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

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/10/Wu_Lerch_2015_Drum-Transcription-using-Partially-Fixed-Non-Negative-Matrix-Factorization-With.pdf},

year  = {2015},

date = {2015-01-01},

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

publisher = {ISMIR},

address = {Malaga},

abstract = {In this paper, a template adaptive drum transcription algo- 

rithm using partially fixed Non-negative Matrix Factoriza- 

tion (NMF) is presented. The proposed method detects per- 

cussive events in complex mixtures of music with a minimal 

training set. The algorithm decomposes the music signal 

into two dictionaries: a percussive dictionary initialized 

with pre-defined drum templates and a harmonic dictionary 

initialized with undefined entries. The harmonic dictionary 

is adapted to the non-percussive music content in a standard 

NMF procedure. The percussive dictionary is adapted to 

each individual signal in an iterative scheme: it is fixed 

during the decomposition process, and is updated based on 

the result of the previous convergence. Two template adap- 

tation methods are proposed to provide more flexibility and 

robustness in the case of unknown data. The performance 

of the proposed system has been evaluated and compared 

to state of the art systems. The results show that template 

adaptation improves the transcription performance, and the 

detection accuracy is in the same range as more complex 

systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhou_chord_2015,

title = {Chord Detection Using Deep Learning},

author = {Xinquan Zhou and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/10/Zhou_Lerch_2015_Chord-Detection-Using-Deep-Learning.pdf},

year  = {2015},

date = {2015-01-01},

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

publisher = {ISMIR},

address = {Malaga},

abstract = {In this paper, we utilize deep learning to learn high-level 

features for audio chord detection. The learned features, 

obtained by a deep network in bottleneck architecture, give 

promising results and outperform state-of-the-art systems. 

We present and evaluate the results for various methods and 

configurations, including input pre-processing, a bottleneck 

architecture, and SVMs vs. HMMs for chord classification.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{coler_cmmsd:_2014,

title = {CMMSD: A Data Set for Note-Level Segmentation of Monophonic Music},

author = {Henrik von Coler and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/04/Coler_Lerch_2014_CMMSD.pdf},

year  = {2014},

date = {2014-01-01},

booktitle = {Proceedings of the AES 53rd International Conference on Semantic Audio},

publisher = {Audio Engineering Society (AES)},

address = {London, UK},

abstract = {A musical data set for note-level segmentation of monophonic music is presented. It contains 36 excerpts from 

commercial recordings of monophonic classical western music and features the instrument groups strings, 

woodwind and brass. The excerpts are self-contained phrases with a mean length of 17.97 seconds and an 

average of 20 notes. All phrases are played in moderate tempo, mostly with significant amounts of expressive 

articulation. A manually annotated ground truth splits each item into a sequence of the three states note, 

transition and rest. The set is designed as an open source project, aiming at the development and evaluation 

of algorithms for segmentation, music performance analysis and feature selection. This paper presents the 

process of ground truth labeling and a detailed description of the data set and its properties.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kraft_tonalness_2013,

title = {The Tonalness Spectrum: Feature-Based Estimation of Tonal Components},

author = {Sebastian Kraft and Alexander Lerch and Udo Z\"{o}lzer},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/04/Kraft%20et%20al_2013_The%20Tonalness%20Spectrum.pdf},

year  = {2013},

date = {2013-01-01},

urldate = {2014-01-16},

booktitle = {Proceedings of the 16th International Conference on Digital Audio Effects},

address = {Maynooth},

abstract = {The tonalness spectrum shows the likelihood of a spectral bin be- 

ing part of a tonal or non-tonal component. It is a non-binary 

measure based on a set of established spectral features. An eas- 

ily extensible framework for the computation, selection, and com- 

bination of features is introduced. The results are evaluated and 

compared in two ways. First with a data set of synthetically gen- 

erated signals but also with real music signals in the context of a 

typical MIR application.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ness_strategies_2011,

title = {Strategies for Orca Call Retrieval to Support Collaborative Annotation of a Large Archive},

author = {Steven R Ness and Alexander Lerch and George Tzanetakis},

url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6093798},

doi = {10.1109/MMSP.2011.6093798},

isbn = {978-1-4577-1434-4},

year  = {2011},

date = {2011-01-01},

booktitle = {Proceedings of the International Workshop on Multimedia Signal Processing (MMSP)},

publisher = {IEEE},

address = {Hangzhou},

abstract = {The Orchive is a large audio archive of hydrophone recordings of Killer whale (Orcinus orca) vocalizations. Researchers and users from around the world can interact with the archive using a collaborative web-based annotation, visualization and retrieval interface. In addition a mobile client has been written in order to crowdsource Orca call annotation. In this paper we describe and compare different strategies for the retrieval of discrete Orca calls. In addition, the results of the automatic analysis are integrated in the user interface facilitating annotation as well as leveraging the existing annotations for supervised learning. The best strategy achieves a mean average precision of 0.77 with the first retrieved item being relevant 95% of the time in a dataset of 185 calls belonging to 4 types.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wiesener_adaptive_2010,

title = {Adaptive Noise Reduction for Real-time Applications},

author = {Constantin Wiesener and Tim Flohrer and Alexander Lerch and Stefan Weinzierl},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2015/04/Wiesener%20et%20al_2010_Adaptive%20Noise%20Reduction%20for%20Real-time%20Applications.pdf},

year  = {2010},

date = {2010-01-01},

booktitle = {Proceedings of the 128th Audio Engineering Society Convention (Preprint #8048)},

publisher = {Audio Engineering Society},

address = {London},

abstract = {We present a new algorithm for real-time noise reduction of audio signals. In order to derive the noise reduction function, the proposed method adaptively estimates the instantaneous noise spectrum from an autoregressive signal model as opposed to the widely-used approach of using a constant noise spectrum fingerprint. In conjunction with the Ephraim and Malah suppression rule a significant reduction of both stationary and non-stationary noise can be obtained. The adaptive algorithm is able to work without user interaction and is capable of real-time processing. Furthermore, quality improvements are easily possible by integration of additional processing blocks such as transient preservation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{yogev_system_2008,

title = {A System for Automatic Audio Harmonization ( Ein System f\"{u}r automatische Audio-Harmonisierung)},

author = {Noam Yogev and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/10/Yogev-and-Lerch-2008-A-System-for-Automatic-Audio-Harmonization-Ein-S-1.pdf},

doi = {10.1.1.148.8391},

year  = {2008},

date = {2008-01-01},

booktitle = {Proceedings of the VdT International Convention (25. Tonmeistertagung)},

address = {Leipzig},

abstract = {A rule-based system for automatic melody harmonization is presented. It models the cognitive process a human arranger undergoes when confronted with the same task, namely: segmenting the melody into phrases, tagging melody notes with harmonic functions, establishing a palette of possible chords for each note, and finding the most agreeable voicing through these chords. The system is designed to be embedded in an audio framework, which synthe- sizes a four-voiced audio output using pitch-shifting techniques. Principles of classical counterpoint as well as common voice-leading conven- tions are utilized by the system. We shall outline the various phases of computa- tion, describe the rules applied in each phase, and present perspectives regarding the stylistic flexibility suggested by the system's design.},

keywords = {audio, harmonization},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lerch_requirement_2006,

title = {On the Requirement of Automatic Tuning Frequency Estimation},

author = {Alexander Lerch},

url = {http://dx.doi.org/10.14279/depositonce-2037},

year  = {2006},

date = {2006-01-01},

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

publisher = {ISMIR},

address = {Victoria},

abstract = {The deviation of the tuning frequency from the standard tuning frequency 440 Hz is evaluated for a database of classical music. It is discussed if and under what circumstances such a deviation may affect the robustness of pitch-based systems for musical content analysis.},

keywords = {frequency, tuning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lerch_feapi:_2005,

title = {FEAPI: A Low Level Feature Extraction Plugin API},

author = {Alexander Lerch and Gunnar Eisenberg and Koen Tanghe},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/10/Lerch-et-al.-2005-FEAPI-A-Low-Level-Feature-Extraction-Plugin-API.pdf},

year  = {2005},

date = {2005-09-01},

booktitle = {Proceedings of 8th International Conference on Digital Audio Effects (DAFX)},

address = {Madrid},

abstract = {This paper presents FEAPI, an easy-to-use platform-independent 

plugin application programming interface (API) for the extraction 

of low level features from audio in PCM format in the context of 

music information retrieval software. The need for and advantages 

of using an open and well-defined plugin interface are outlined in 

this paper and an overview of the API itself and its usage is given.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lerch_ansatz_2004,

title = {Ein Ansatz zur automatischen Erkennung der Tonart in Musikdateien},

author = {Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/10/Lerch-2004-Ein-Ansatz-zur-automatischen-Erkennung-der-Tonart-.pdf},

year  = {2004},

date = {2004-01-01},

booktitle = {Proceedings of the VDT International Audio Convention (23. Tonmeistertagung)},

address = {Leipzig},

abstract = {Es wird ein Verfahren zur automatischen Erkennung der Tonart von Musikdateien vorgestellt. Das Verfahren analysiert mittels einer Filterbank den Tonvorrat des Eingangssignals, der in einem Tonvektor zusammenfasst wird. Dabei sind sowohl mehrstimmige als auch ein- stimmige Eingangssignale zul\"{a}ssig. Mit Hilfe eines Nearest-Neighbour-Classifiers wird anschlie\ss end das wahrscheinlichste Ergebnis f\"{u}r den extrahierten Tonvektor bestimmt. Parallel zur Analyse des Tonvorrats wird die Stimmh\"{o}he des Kammertons detektiert, um eine gleichbleibende Erkennungsrate f\"{u}r Signale unterschiedlicher Stimmh\"{o}he zu gew\"{a}hrleisten.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{burred_hierarchical_2003,

title = {A Hierarchical Approach to Automatic Musical Genre Classification},

author = {Juan Jos\'{e} Burred and Alexander Lerch},

url = {http://www.musicinformatics.gatech.edu/wp-content_nondefault/uploads/2016/10/Burred-and-Lerch-2003-A-Hierarchical-Approach-to-Automatic-Musical-Genre.pdf},

doi = {10.1.1.2.6582},

year  = {2003},

date = {2003-01-01},

booktitle = {Proceedings of the 6th International Conference on Digital Audio Effects (DAFX)},

address = {London},

abstract = {A system for the automatic classification of audio signals according to audio category is presented. The signals are recognized as speech, background noise and one of 13 musical genres. A large number of audio features are evaluated for their suitability in such a classification task, including well-known physical and perceptual features, audio descriptors defined in the MPEG-7 standard, as well as new features proposed in this work. These are selected with regard to their ability to distinguish between a given set of audio types and to their robustness to noise and bandwidth changes. In contrast to previous systems, the feature selection and the classification process itself are carried out in a hierarchical way. This is motivated by the numerous advantages of such a tree-like structure, which include easy expansion capabilities, flexibility in the design of genre-dependent features and the ability to reduce the probability of costly errors. The resulting application is evaluated with respect to classification accuracy and computational costs.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}