Lerch, Alexander Audioinhaltsanalyse Book Section In: Weinzierl, Stefan (Ed.): Handbuch der Audiotechnik, pp. 1–20, Springer Berlin Heidelberg, Berlin, Heidelberg, 2023, ISBN: 978-3-662-60357-4. Abstract | Links | BibTeX | Tags: Audio content analysis, Grundfrequenzerkennung, music information retrieval, Musikklassifizierung, Musiktranskription, Tonarterkennung Lerch, Alexander An Introduction to Audio Content Analysis: Music Information Retrieval Tasks and Applications Book 2, Wiley-IEEE Press, Hoboken, N.J, 2023, ISBN: 978-1-119-89094-2. Abstract | Links | BibTeX | Tags: analysis, audio, Audio content analysis, audio signal processing, Automatic Music Transcription, Computer sound processing, machine listening, Matlab, MIR, music analysis, music informatics, music information retrieval, Python Lerch, Alexander libACA, pyACA, and ACA-Code: Audio Content Analysis in 3 Languages Journal Article In: Software Impacts, pp. 100349, 2022, ISSN: 2665-9638. Abstract | Links | BibTeX | Tags: Audio content analysis, C++, Matlab, music information retrieval, Python Pati, Kumar Ashis; Gururani, Siddharth; Lerch, Alexander Assessment of Student Music Performances Using Deep Neural Networks Journal Article In: Applied Sciences, vol. 8, no. 4, pp. 507, 2018. Abstract | Links | BibTeX | Tags: deep learning, deep neural networks, DNN, MIR, music education, music informatics, music information retrieval, music learning, music performance assessment Lu, Yen-Cheng; Wu, Chih-Wei; Lu, Chang-Tien; Lerch, Alexander An Unsupervised Approach to Anomaly Detection in Music Datasets Proceedings Article In: Proceedings of the ACM SIGIR Conference (SIGIR), pp. 749–752, ACM, Pisa, 2016, ISBN: 978-1-4503-4069-4. Abstract | Links | BibTeX | Tags: anomaly detection, data clean-up, music genre retrieval, music information retrieval Lu, Yen-Cheng; Wu, Chih-Wei; Lu, Chang-Tien; Lerch, Alexander Automatic Outlier Detection in Music Genre Datasets Proceedings Article In: Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), ISMIR, New York, 2016. Abstract | Links | BibTeX | Tags: anomaly detection, data clean-up, music genre retrieval, music information retrieval Lerch, Alexander An Introduction to Audio Content Analysis: Applications in Signal Processing and Music Informatics Book Wiley-IEEE Press, Hoboken, 2012, ISBN: 978-1-118-26682-3. Abstract | Links | BibTeX | Tags: analysis, audio, audio signal processing, information, listening, machine, machine listening, music, music analysis, music information retrieval, processing, retrieval, signal2023
@incollection{lerch_audioinhaltsanalyse_2023,
title = {Audioinhaltsanalyse},
author = {Alexander Lerch},
editor = {Stefan Weinzierl},
url = {https://doi.org/10.1007/978-3-662-60357-4_8-1},
doi = {10.1007/978-3-662-60357-4_8-1},
isbn = {978-3-662-60357-4},
year = {2023},
date = {2023-01-01},
urldate = {2023-03-30},
booktitle = {Handbuch der Audiotechnik},
pages = {1--20},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
abstract = {Audiosignale enthalten eine F\"{u}lle von Informationen, die sich Menschen beim H\"{o}ren leicht erschlie\ssen. So transportiert ein Sprachsignal nicht nur Informationen \"{u}ber den Text, sondern auch \"{u}ber den Sprecher (z. B. Geschlecht, Alter, Akzent) und die Aufnahmeumgebung (z. B. drinnen vs. drau\ssen). In einem Musiksignal k\"{o}nnen wir die Musikinstrumente, die musikalische Struktur, den Stil, die Melodie, Harmonien und Tonalit\"{a}t, einen emotionalen Ausdruck und andere Charakteristika der Darbietung sowie das K\"{o}nnen der Vortragenden identifizieren. Die Audioinhaltsanalyse (Audio Content Analysis, ACA) zielt darauf ab, Algorithmen zur automatischen Extraktion dieser Inhalte aus dem (digitalen) Audiosignal zu entwickeln und einzusetzen; diese Algorithmen erm\"{o}glichen es uns, das Audiosignal basierend auf dem Inhalt zu sortieren, zu kategorisieren, zu segmentieren und zu visualisieren (Lerch 2012). M\"{o}gliche Anwendungen sind inhaltsbasierte automatische Playlist-Generierung und Musikempfehlungssysteme, computergest\"{u}tzte Musikproduktion und -bearbeitung sowie intelligente Musiklernprogramme, die Musiksch\"{u}lerinnen und -sch\"{u}ler auf Fehler und Verbesserungsm\"{o}glichkeiten beim Instrumentalspiel hinweisen.},
keywords = {Audio content analysis, Grundfrequenzerkennung, music information retrieval, Musikklassifizierung, Musiktranskription, Tonarterkennung},
pubstate = {published},
tppubtype = {incollection}
}
@book{lerch_introduction_2023,
title = {An Introduction to Audio Content Analysis: Music Information Retrieval Tasks and Applications},
author = {Alexander Lerch},
url = {https://ieeexplore.ieee.org/servlet/opac?bknumber=9965970},
isbn = {978-1-119-89094-2},
year = {2023},
date = {2023-01-01},
urldate = {2022-01-01},
publisher = {Wiley-IEEE Press},
address = {Hoboken, N.J},
edition = {2},
abstract = {An Introduction to Audio Content Analysis Enables readers to understand the algorithmic analysis of musical audio signals with AI-driven approaches An Introduction to Audio Content Analysis serves as a comprehensive guide on audio content analysis explaining how signal processing and machine learning approaches can be utilized for the extraction of musical content from audio. It gives readers the algorithmic understanding to teach a computer to interpret music signals and thus allows for the design of tools for interacting with music. The work ties together topics from audio signal processing and machine learning, showing how to use audio content analysis to pick up musical characteristics automatically. A multitude of audio content analysis tasks related to the extraction of tonal, temporal, timbral, and intensity-related characteristics of the music signal are presented. Each task is introduced from both a musical and a technical perspective, detailing the algorithmic approach as well as providing practical guidance on implementation details and evaluation. To aid in reader comprehension, each task description begins with a short introduction to the most important musical and perceptual characteristics of the covered topic, followed by a detailed algorithmic model and its evaluation, and concluded with questions and exercises. For the interested reader, updated supplemental materials are provided via an accompanying website. Written by a well-known expert in the music industry, sample topics covered in Introduction to Audio Content Analysis include: Digital audio signals and their representation, common time-frequency transforms, audio features Pitch and fundamental frequency detection, key and chord Representation of dynamics in music and intensity-related features Beat histograms, onset and tempo detection, beat histograms, and detection of structure in music, and sequence alignment Audio fingerprinting, musical genre, mood, and instrument classification An invaluable guide for newcomers to audio signal processing and industry experts alike, An Introduction to Audio Content Analysis covers a wide range of introductory topics pertaining to music information retrieval and machine listening, allowing students and researchers to quickly gain core holistic knowledge in audio analysis and dig deeper into specific aspects of the field with the help of a large amount of references.},
keywords = {analysis, audio, Audio content analysis, audio signal processing, Automatic Music Transcription, Computer sound processing, machine listening, Matlab, MIR, music analysis, music informatics, music information retrieval, Python},
pubstate = {published},
tppubtype = {book}
}
2022
@article{lerch_libaca_2022-1,
title = {libACA, pyACA, and ACA-Code: Audio Content Analysis in 3 Languages},
author = {Alexander Lerch},
url = {https://www.sciencedirect.com/science/article/pii/S2665963822000677},
doi = {10.1016/j.simpa.2022.100349},
issn = {2665-9638},
year = {2022},
date = {2022-07-01},
urldate = {2022-07-04},
journal = {Software Impacts},
pages = {100349},
abstract = {The three packages libACA, pyACA, and ACA-Code provide reference implementations for basic approaches and algorithms for the analysis of musical audio signals in three different languages: C++, Python, and Matlab. All three packages cover the same algorithms, such as extraction of low level audio features, fundamental frequency estimation, as well as simple approaches to chord recognition, musical key detection, and onset detection. In addition, it implementations of more generic algorithms useful in audio content analysis such as dynamic time warping and the Viterbi algorithm are provided. The three packages thus provide a practical cross-language and cross-platform reference to students and engineers implementing audio analysis algorithms and enable implementation-focused learning of algorithms for audio content analysis and music information retrieval.},
keywords = {Audio content analysis, C++, Matlab, music information retrieval, Python},
pubstate = {published},
tppubtype = {article}
}
2018
@article{pati_assessment_2018,
title = {Assessment of Student Music Performances Using Deep Neural Networks},
author = {Kumar Ashis Pati and Siddharth Gururani and Alexander Lerch},
url = {http://www.mdpi.com/2076-3417/8/4/507/pdf},
doi = {10.3390/app8040507},
year = {2018},
date = {2018-01-01},
urldate = {2018-03-27},
journal = {Applied Sciences},
volume = {8},
number = {4},
pages = {507},
abstract = {Music performance assessment is a highly subjective task often relying on experts to gauge both the technical and aesthetic aspects of the performance from the audio signal. This article explores the task of building computational models for music performance assessment, i.e., analyzing an audio recording of a performance and rating it along several criteria such as musicality, note accuracy, etc. Much of the earlier work in this area has been centered around using hand-crafted features intended to capture relevant aspects of a performance. However, such features are based on our limited understanding of music perception and may not be optimal. In this article, we propose using Deep Neural Networks (DNNs) for the task and compare their performance against a baseline model using standard and hand-crafted features. We show that, using input representations at different levels of abstraction, DNNs can outperform the baseline models across all assessment criteria. In addition, we use model analysis techniques to further explain the model predictions in an attempt to gain useful insights into the assessment process. The results demonstrate the potential of using supervised feature learning techniques to better characterize music performances.},
keywords = {deep learning, deep neural networks, DNN, MIR, music education, music informatics, music information retrieval, music learning, music performance assessment},
pubstate = {published},
tppubtype = {article}
}
2016
@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}
}
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.2012
@book{lerch_introduction_2012,
title = {An Introduction to Audio Content Analysis: Applications in Signal Processing and Music Informatics},
author = {Alexander Lerch},
url = {http://ieeexplore.ieee.org/xpl/bkabstractplus.jsp?bkn=6266785},
isbn = {978-1-118-26682-3},
year = {2012},
date = {2012-01-01},
publisher = {Wiley-IEEE Press},
address = {Hoboken},
abstract = {With the proliferation of digital audio distribution over digital media, audio content analysis is fast becoming a requirement for designers of intelligent signal-adaptive audio processing systems. Written by a well-known expert in the field, this book provides quick access to different analysis algorithms and allows comparison between different approaches to the same task, making it useful for newcomers to audio signal processing and industry experts alike. A review of relevant fundamentals in audio signal processing, psychoacoustics, and music theory, as well as downloadable MATLAB files are also included. Please visit the companion website: www.AudioContentAnalysis.org},
keywords = {analysis, audio, audio signal processing, information, listening, machine, machine listening, music, music analysis, music information retrieval, processing, retrieval, signal},
pubstate = {published},
tppubtype = {book}
}
publications
Audioinhaltsanalyse Book Section In: Weinzierl, Stefan (Ed.): Handbuch der Audiotechnik, pp. 1–20, Springer Berlin Heidelberg, Berlin, Heidelberg, 2023, ISBN: 978-3-662-60357-4. An Introduction to Audio Content Analysis: Music Information Retrieval Tasks and Applications Book 2, Wiley-IEEE Press, Hoboken, N.J, 2023, ISBN: 978-1-119-89094-2. libACA, pyACA, and ACA-Code: Audio Content Analysis in 3 Languages Journal Article In: Software Impacts, pp. 100349, 2022, ISSN: 2665-9638. Assessment of Student Music Performances Using Deep Neural Networks Journal Article In: Applied Sciences, vol. 8, no. 4, pp. 507, 2018. An Unsupervised Approach to Anomaly Detection in Music Datasets Proceedings Article In: Proceedings of the ACM SIGIR Conference (SIGIR), pp. 749–752, ACM, Pisa, 2016, ISBN: 978-1-4503-4069-4. Automatic Outlier Detection in Music Genre Datasets Proceedings Article In: Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), ISMIR, New York, 2016. An Introduction to Audio Content Analysis: Applications in Signal Processing and Music Informatics Book Wiley-IEEE Press, Hoboken, 2012, ISBN: 978-1-118-26682-3.2023
2022
2018
2016
2012