Music transcription with ISA and HMM - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2004

Music transcription with ISA and HMM

Abstract

We propose a new generative model for polyphonic music based on nonlinear Independent Subspace Analysis (ISA) and factorial Hidden Markov Models (HMM). ISA represents chord spectra as sums of note power spectra and note spectra as sums of instrument-dependent log-power spectra. HMM models note duration. Instrument-dependent parameters are learnt on solo excerpts and used to transcribe musical recordings as collections of notes with time-varying power and other descriptive parameters such as vibrato. We prove the relevance of our modeling assumptions by comparing them with true data distributions and by giving satisfying transcriptions of two duo recordings.
Fichier principal
Vignette du fichier
vincent_ICA04bis.pdf (482.75 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00544697 , version 1 (08-12-2010)

Identifiers

  • HAL Id : inria-00544697 , version 1

Cite

Emmanuel Vincent, Xavier Rodet. Music transcription with ISA and HMM. 5th Int. Conf. on Independent Component Analysis and Blind Signal Separation (ICA), Sep 2004, Granada, Spain. pp.1197--1204. ⟨inria-00544697⟩

Collections

IRCAM
79 View
265 Download

Share

Gmail Facebook Twitter LinkedIn More