An Information-theoretic Approach to Machine-oriented Music Summarization

Music summarization allows for higher efficiency in processing, storage, and sharing of datasets. Machine-oriented approaches, being agnostic to human consumption, optimize these aspects even further. Such summaries have already been successfully validated in some MIR tasks. We now generalize previous conclusions by evaluating the impact of generic summarization of music from a probabilistic perspective. We estimate Gaussian distributions for original and summarized songs and compute their relative entropy, in order to measure information loss incurred by summarization. Our results suggest that relative entropy is a good predictor of summarization performance in the context of tasks relying on a bag-of-features model. Based on this observation, we further propose a straightforward yet expressive summarizer, which minimizes relative entropy with respect to the original song, that objectively outperforms previous methods and is better suited to avoid potential copyright issues.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  Ricardo Ribeiro,et al.  On the Application of Generic Summarization Algorithms to Music , 2015, IEEE Signal Processing Letters.

[3]  J. Steinberger,et al.  Using Latent Semantic Analysis in Text Summarization and Summary Evaluation , 2004 .

[4]  T. Eerola,et al.  A comparison of the discrete and dimensional models of emotion in music , 2011 .

[5]  Björn W. Schuller,et al.  Recent developments in openSMILE, the munich open-source multimedia feature extractor , 2013, ACM Multimedia.

[6]  Jade Goldstein-Stewart,et al.  The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries , 1998, SIGIR Forum.

[7]  Dragomir R. Radev,et al.  LexRank: Graph-based Lexical Centrality as Salience in Text Summarization , 2004, J. Artif. Intell. Res..

[8]  Elias Pampalk,et al.  Content-based organization and visualization of music archives , 2002, MULTIMEDIA '02.

[9]  Ewa Łukasik,et al.  Automatic Music Summarization. A “Thumbnail” Approach , 2011 .

[10]  Eenjun Hwang,et al.  Music segmentation and summarization based on self-similarity matrix , 2013, ICUIMC '13.

[11]  Stephen M. Chu,et al.  MUSIC SUMMARY USING KEY PHRASES , 2000 .

[12]  Petri Toiviainen,et al.  MIR in Matlab (II): A Toolbox for Musical Feature Extraction from Audio , 2007, ISMIR.

[13]  Xavier Rodet,et al.  Toward Automatic Music Audio Summary Generation from Signal Analysis , 2002, ISMIR.

[14]  Xin Liu,et al.  Generic text summarization using relevance measure and latent semantic analysis , 2001, SIGIR '01.

[15]  E. B. Newman,et al.  A Scale for the Measurement of the Psychological Magnitude Pitch , 1937 .

[16]  W. Marsden.  I and J , 2012 .

[17]  Conrad Sanderson,et al.  Armadillo: An Open Source C++ Linear Algebra Library for Fast Prototyping and Computationally Intensive Experiments , 2010 .

[18]  R. Thayer.  The biopsychology of mood and arousal , 1989 .

[19]  Xavier Rodet,et al.  Signal-based Music Structure Discovery for Music Audio Summary Generation , 2003, ICMC.

[20]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[21]  C. Harte,et al.  Detecting harmonic change in musical audio , 2006, AMCMM '06.

[22]  Homer H. Chen,et al.  Music Emotion Recognition , 2011 .

[23]  Alexander H. Waibel,et al.  Minimizing Word Error Rate in Textual Summaries of Spoken Language , 2000, ANLP.

[24]  Franz de Leon,et al.  USING TIMBRE MODELS FOR AUDIO CLASSIFICATION , 2013 .

[25]  David Martins de Matos,et al.  Summarization of films and documentaries based on subtitles and scripts , 2015, Pattern Recognit. Lett..

[26]  Gregory H. Wakefield,et al.  Audio thumbnailing of popular music using chroma-based representations , 2005, IEEE Transactions on Multimedia.

[27]  George Tzanetakis,et al.  MARSYAS: a framework for audio analysis , 1999, Organised Sound.

[28]  J. Russell.  A circumplex model of affect. , 1980 .

[29]  Emilia Gómez Gutiérrez,et al.  Tonal description of music audio signals , 2006 .

[30]  Wei Chai,et al.  Semantic segmentation and summarization of music: methods based on tonality and recurrent structure , 2006, IEEE Signal Processing Magazine.

[31]  Jean Carletta,et al.  Extractive summarization of meeting recordings , 2005, INTERSPEECH.

[32]  Elias Pampalk.  A Matlab Toolbox to Compute Music Similarity from Audio , 2004, ISMIR.

[33]  Jade Goldstein-Stewart,et al.  The use of MMR, diversity-based reranking for reordering documents and producing summaries , 1998, SIGIR '98.

[34]  P. Mahalanobis.  On the generalized distance in statistics , 1936 .

[35]  Matthew Cooper,et al.  Summarizing popular music via structural similarity analysis , 2003, 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684).

[36]  Halina Kwasnicka,et al.  Similarity-Based Summarization of Music Files for Support Vector Machines , 2018, Complex..

[37]  Ani Nenkova,et al.  Automatically Assessing Machine Summary Content Without a Gold Standard , 2013, CL.

[38]  M. Picheny,et al.  Comparison of Parametric Representation for Monosyllabic Word Recognition in Continuously Spoken Sentences , 2017 .

[39]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[40]  Ricardo Ribeiro,et al.  Using Generic Summarization to Improve Music Information Retrieval Tasks , 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[41]  Huaiyu Zhu.  On Information and Sufficiency , 1997 .

[42]  Xiaojin Zhu,et al.  Improving Diversity in Ranking using Absorbing Random Walks , 2007, NAACL.

[43]  Jonathan Foote,et al.  Automatic Music Summarization via Similarity Analysis , 2002, ISMIR.

[44]  Ricardo Ribeiro,et al.  Revisiting Centrality-as-Relevance: Support Sets and Similarity as Geometric Proximity: Extended abstract , 2013, IJCAI.