Statistical Natural Language Processing Methods in Music Notation Analysis
| Thesis title in Czech: | Statistical Natural Language Processing Methods in Music Notation Analysis |
|---|---|
| Thesis title in English: | Statistical Natural Language Processing Methods in Music Notation Analysis |
| English key words: | statistical melody modeling, music notation, NLP methods, audio melody extraction |
| Academic year of topic announcement: | 2011/2012 |
| Thesis type: | diploma thesis |
| Thesis language: | angličtina |
| Department: | Institute of Formal and Applied Linguistics (32-UFAL) |
| Supervisor: | Mgr. Nino Peterek, Ph.D. |
| Author: | hidden - assigned and confirmed by the Study Dept. |
| Date of registration: | 03.08.2011 |
| Date of assignment: | 06.10.2011 |
| Confirmed by Study dept. on: | 14.10.2011 |
| Date and time of defence: | 20.05.2013 09:00 |
| Date of electronic submission: | 12.04.2013 |
| Date of submission of printed version: | 12.04.2013 |
| Date of proceeded defence: | 20.05.2013 |
| Opponents: | RNDr. David Mareček, Ph.D. |
| Guidelines |
| It has been more than 180 years since the American poet H. W. Longfellow wrote in his book "A Pilgrimage Beyond the Sea" often quoted and now well-known sentence: "Music is the universal language of mankind." He was definitely neither the first or the last one who had such ideas. Obviously, his thought behind this sentence was something slightly different at the beginning of Romantic era than any explicit relation between music and language. But anyway, comparing and finding similarities between music and language appear thorough the whole history of science and art. The most probable prehistorical vocal origin of music, from the non-linguistic utterances as expressing happiness or crying and weeping, just proves proximity of such relation.
Importance of the language-music relation shows how often composers and theoreticians of music were interested in such question. A good example of it can be a Czech composer, Leoš Janáček, who studied at the beginning of the 20-th century melody of speech in order to use natural melody of utterances in his operas. For many years he collected in his notebooks "speech tunes" of people speaking around him and then used them while composing, because he strongly believed there is a close connection between natural language and natural tuniness. The concrete goals of the thesis are to explore different ways of parsing scores and to explore the statistical properties of such ways of parsing. The final result should be a music notation model constructed the same as the language models are. |
| References |
| Leonard B. Meyer, Meaning in Music and Information Theory, The Journal of Aesthetics and Art Criticism, Vol. 15, No. 4 (Jun., 1957), pp. 412-424, Blackwell Publishing on behalf of The American Society for Aesthetics
Ian H. Witten, Leonard C. Manzara, Darrell Conklin, Computer Music Journal, Vol. 18, No. 1 (Spring, 1994), pp. 70-80, The MIT Press Chris Dobrian, Music and Language (1992), http://music.arts.uci.edu/dobrian/CD.music.lang.htm Wolkowicz, J., S. Brooks, and V. Keselj (2009), Midivis: Visualizing music structure via similarity matrices, In Proceedings of the International Computer Music Conference (ICMC), Montreal, QC, Canada, 53–6 Manning, C. D., Schuetze, H. (1999), Foundations of statistical natural language processing, Cambridge Massachusetts: MIT Press Sudhoff, Stefan, Denisa Lenertová, Roland Meyer, Sandra Pappert, Petra Augurzky, Ina Mleinek, Nicole Richter & Johannes, Schließer (eds.) (2006), Methods in empirical prosody research, (Language, Context, and Cognition; 3), Berlin/New York: Walter de Gruyter |