The Markov selection model for concurrent speech recognition

Paris Smaragdis, Bhiksha Raj

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

Abstract

In this paper we introduce a new Markov model that is capable of recognizing speech from recordings of simultaneously speaking a priori known speakers. This work is based on recent work on non-negative representations of spectrograms, which has been shown to be very effective in source separation problems. In this paper we extend these approaches to design a Markov selection model that is able to recognize sequences even when they are presented mixed together. We do so without the need to perform separation on the signals. Unlike factorial Markov models which have been used similarly in the past, this approach features a low computational complexity in the number of sources and Markov states, which makes it a highly efficient alternative. We demonstrate the use of this framework in recognizing speech from mixtures of known speakers.

Original languageEnglish (US)
Title of host publicationProceedings of the 2010 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2010
Pages214-219
Number of pages6
DOIs
StatePublished - 2010
Externally publishedYes
Event2010 IEEE 20th International Workshop on Machine Learning for Signal Processing, MLSP 2010 - Kittila, Finland
Duration: Aug 29 2010Sep 1 2010

Publication series

NameProceedings of the 2010 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2010

Other

Other2010 IEEE 20th International Workshop on Machine Learning for Signal Processing, MLSP 2010
CountryFinland
CityKittila
Period8/29/109/1/10

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing

Fingerprint Dive into the research topics of 'The Markov selection model for concurrent speech recognition'. Together they form a unique fingerprint.

Cite this