Home » Conference Paper, Publication

A Deterministic Annealing Algorithm for Automatic Music Transcription

PDF BIBTEX   28 Januar 2014 1,186 views No Comment
Publication authored by Tian Cheng and Matthias Mauch and Simon Dixon.

Abstract: In the past decade, non-negative matrix factorisation (NMF) and probabilistic latent component analysis (PLCA) have been used widely in automatic music transcription. Despite their successes, these methods only guarantee that the decomposition converges to a local minimum in the cost function. In order to find better local minima, we propose to extend an existing PLCA-based transcription method with the deterministic annealing EM (DAEM) algorithm. The PLCA update rules are modified by introducing a “temperature” parameter. At higher temperatures, general areas of the search space containing good solutions are found. As the temperature is gradually decreased, distinctions in the data are sharpened, resulting in a more fine-grained optimisation at each successive temperature. This process reduces the dependence on the initialisation, which is otherwise a limitation of NMF and PLCA approaches. The method was tested on two standard multi-instrument transcription data sets (MIREX and Bach10). Experimental results show that the proposed method significantly out-performs a state-of-the-art reference method, according to both frame-based and note-based metrics. An additional analysis of instrument assignment results shows that instrument spectra are typically modelled as mixtures of templates from several instruments.

Bibtex:

@inproceedings{cheng_dae_2013,

author = {Cheng, Tian and Dixon, Simon and Mauch, Matthias},

booktitle = {Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR 2013)},

title = {A Deterministic Annealing Algorithm for Automatic Music Transcription},

year = {2013}

}

Comments are closed.