Multi-voice polyphonic music transcription using eigeninstruments
Authors:
- 1 October 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 53-56
Abstract
We present a model-based approach to separating and transcribing single-channel, multi-instrument polyphonic music in a semi-blind fashion. Our system extends the non-negative matrix factorization (NMF) algorithm to incorporate constraints on the basis vectors of the solution. In the context of music transcription, this allows us to encode prior knowledge about the space of possible instrument models as a parametric subspace we term ldquoeigeninstrumentsrdquo. We evaluate our algorithm on several synthetic (MIDI) recordings containing different instrument mixtures. Averaged over both sources, we achieved a frame-level accuracy of over 68% on an excerpt of Pachelbel's Canon arranged for doublebass and piano and 72% on a mixture of overlapping melodies played by flute and violin.Keywords
This publication has 6 references indexed in Scilit:
- Monaural Speech Separation using Source-Adapted Models2007
- Improving Generalization for Classification-Based Polyphonic Piano Transcription2007
- Non-negative Matrix Factor Deconvolution; Extraction of Multiple Sound Sources from Monophonic Inputs2004
- Non-negative matrix factorization for polyphonic music transcription2004
- Multiple fundamental frequency estimation based on harmonicity and spectral smoothnessIEEE Transactions on Speech and Audio Processing, 2003
- Rapid speaker adaptation in eigenvoice spaceIEEE Transactions on Speech and Audio Processing, 2000