publications

@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}

}

@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}

}