Simultaneous noise classification and reduction using a priori learned models

Nasser Mohammadiha, Paris Smaragdis, Arne Leijon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Classifying the acoustic environment is an essential part of a practical supervised source separation algorithm where a model is trained for each source offline. In this paper, we present a classification scheme that is combined with a probabilistic nonnegative matrix factorization (NMF) based speech denoising algorithm. We model the acoustic environment with a hidden Markov model (HMM) whose emission distributions are assumed to be of NMF type. We derive a minimum mean square error (MMSE) estimator of clean speech signal in which the state-dependent speech estimators are weighted according to the state posterior probabilities (or probabilities of different noise environments) and are summed. Our experiments show that the proposed method outperforms state-of-the-art substantially and that its performance is very close to an oracle case where the noise type is known in advance.

Original languageEnglish (US)
Title of host publication2013 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2013
DOIs
StatePublished - Dec 1 2013
Event2013 16th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2013 - Southampton, United Kingdom
Duration: Sep 22 2013Sep 25 2013

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
ISSN (Print)2161-0363
ISSN (Electronic)2161-0371

Other

Other2013 16th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2013
CountryUnited Kingdom
CitySouthampton
Period9/22/139/25/13

Keywords

  • Nonnegative matrix factorization
  • acoustic environment classification
  • supervised speech enhancement

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing

Fingerprint Dive into the research topics of 'Simultaneous noise classification and reduction using a priori learned models'. Together they form a unique fingerprint.

Cite this