Infinite-state spectrum model for music signal analysis

This paper presents a nonparametric Bayesian extension of nonnegative matrix factorization (NMF) for music signal analysis. Instrument sounds often exhibit non-stationary spectral characteristics. We introduce infinite-state spectral bases into NMF to represent time-varying spectra in polyphonic music signals. We describe our extension of NMF with infinite-state spectral bases generated by the Dirichlet process in a statistical framework, derive an efficient optimization algorithm based on collapsed variational inference, and validate the framework on audio data.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Masahiro Nakano, Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono, Shigeki Sagayama
• Keywords: ICASSP 2011, Infinite-state Spectral Bases, Music Signals, Non-stationary Spectral Characteristics, Signal Processing