Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
The synergy between bounded-distance HMM and spectral subtraction for robust speech recognition
KTH, School of Electrical Engineering (EES), Sound and Image Processing.
2010 (English)In: Speech Communication, ISSN 0167-6393, E-ISSN 1872-7182, Vol. 52, no 2, 123-133 p.Article in journal (Refereed) Published
Abstract [en]

Additive noise generates important losses in automatic speech recognition systems. In this paper, we show that one of the causes contributing to these losses is the fact that conventional recognisers take into consideration feature values that are outliers. The method that we call bounded-distance HMM is a suitable method to avoid that outliers contribute to the recogniser decision. However, this method just deals with outliers, leaving the remaining features unaltered. In contrast, spectral subtraction is able to correct all the features at the expense of introducing some artifacts that, as shown in the paper, cause a larger number of outliers. As a result, we find that bounded-distance HMM and spectral subtraction complement each other well. A comprehensive experimental evaluation was conducted, considering several well-known ASR tasks (of different complexities) and numerous noise types and SNRs. The achieved results show that the suggested combination generally outperforms both the bounded-distance HMM and spectral subtraction individually. Furthermore, the obtained improvements, especially for low and medium SNRs, are larger than the sum of the improvements individually obtained by bounded-distance HMM and spectral subtraction.

Place, publisher, year, edition, pages
2010. Vol. 52, no 2, 123-133 p.
Keyword [en]
Robust speech recognition, Spectral subtraction, Acoustic backing-off, Bounded-distance HMM, Missing features, Outliers, noise, features
Identifiers
URN: urn:nbn:se:kth:diva-19050DOI: 10.1016/j.specom.2009.09.002ISI: 000272764100004Scopus ID: 2-s2.0-70449133421OAI: oai:DiVA.org:kth-19050DiVA: diva2:337097
Note
QC 20100525Available from: 2010-08-05 Created: 2010-08-05 Last updated: 2017-12-12Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Kleijn, W. Bastiaan
By organisation
Sound and Image Processing
In the same journal
Speech Communication

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 42 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf