Construction method of acoustic models dealing with various background noises based on combination of HMMs

Motoyuki Suzuki, Yusuke Kato, Akinori Ito, Shozo Makino

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)

Abstract

Background noise is one of the biggest problem for speech recognition systems in real environments. In order to achieve high recognition performance for corrupted speech, we proposed a new construction method of HMMs dealing with various kinds of background noise. At first, each HMM dealing with a single noise is trained for each background noise, and then all Gaussian components of those HMMs are combined into a "multi-mixture HMM". From the experimental results, the multi-mixture HMM gave the highest recognition performance for any kind of noise and any variation of SNR. Although the multi-mixture HMMs has high performance, it has a huge number of Gaussian components that makes the speech recognition slower. In order to solve the problem, we also proposed a reduction method of Gaussian components. It can decrease the number of Gaussian components with slight deterioration of recognition performance.

Original languageEnglish
Pages973-976
Number of pages4
Publication statusPublished - 2005 Dec 1
Event9th European Conference on Speech Communication and Technology - Lisbon, Portugal
Duration: 2005 Sep 42005 Sep 8

Other

Other9th European Conference on Speech Communication and Technology
CountryPortugal
CityLisbon
Period05/9/405/9/8

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Construction method of acoustic models dealing with various background noises based on combination of HMMs'. Together they form a unique fingerprint.

Cite this