It is the f(MIR) workshop – The Future of MIR – What will MIR be like in 5 or 20 years?
This is the f(MIR) session. Always a highlight at ISMIR
Predicting Development of Research in Music Based on Parallels with Natural Language Processing
Jacek Wołkowicz and Vlado Kešelj
ABSTRACT - The hypothesis of the paper is that the domain of Nat- ural Languages Processing (NLP) resembles current re- search in music so one could benefit from this by employ- ing NLP techniques to music. In this paper the similarity between both domains is described. The levels of NLP are listed with pointers to respective tasks within the research of computational music. A brief introduction to history of NLP enables locating music research in this history. Pos- sible directions of research in music, assuming its affinity to NLP, are introduced. Current research in generational and statistical music modeling is compared to similar NLP theories. The paper is concluded with guidelines for music research and information retrieval.
Notes: The speaker points out the similarities and differences between NLP and MIR.
- Most people are illiterates (i.e. can’t read/write music)
- Much more complex representation
- Limited space of all possible pieces (not sure I agree, the argument is that anyone can generate text/speech, but not so much for music)
History of NLP
- Grammars, Chomsky, Turing Test
- Period of optimism: automatic translation – but failed
- Data mining and statistical methods. Large corpora, brown, wordnet
- Semantics defined by statistics
Algorithms vs. Data: Algorithms don’t matter much, it is all about the data. More data is better.
Comparing Music Objects: similar to the Text Translation problem
What needs to be done:
- Web crawling companies need to give MIR more data
- Convince publishers to annotate data
- Collect parallel data (MIDI / audio)