Various Information Sources for HMM with Weighted Multiple Codebooks

Beitrag bei einer Tagung
(Konferenzbeitrag)


Details zur Publikation

Autor(en): Hacker C, Stemmer G, Steidl S, Nöth E, Niemann H
Herausgeber: Wendemuth A.
Verlag: -
Verlagsort: -
Jahr der Veröffentlichung: 2003
Tagungsband: Proceedings of the Speech Processing Workshop, Magdeburg, Germany, September 09
Seitenbereich: 9-16
Sprache: Englisch


Abstract


When semicontinuous HMM are used for acoustic modeling in speech recognition usually all states share a single code book. In our investigations we split the feature set into independent subsets and use separate codebooks for each part. This provides a higher modeling flexibility while keeping the parameter space compact. Further experiments integrate new information sources by using additional codebooks which are estimated in a supervised training. For instance codebooks for phone transitions are applied. Codebook exponents weight the different information sources. Relative reductions in word error rate up to 20 % have been achieved.


FAU-Autoren / FAU-Herausgeber

Niemann, Heinrich Prof. Dr.
Technische Fakultät
Nöth, Elmar Prof. Dr.-Ing.
Professur für Informatik (Mustererkennung)
Steidl, Stefan PD Dr.
Lehrstuhl für Informatik 5 (Mustererkennung)


Zitierweisen

APA:
Hacker, C., Stemmer, G., Steidl, S., Nöth, E., & Niemann, H. (2003). Various Information Sources for HMM with Weighted Multiple Codebooks. In Wendemuth A. (Eds.), Proceedings of the Speech Processing Workshop, Magdeburg, Germany, September 09 (pp. 9-16). Magdeburg, DE: -: -.

MLA:
Hacker, Christian, et al. "Various Information Sources for HMM with Weighted Multiple Codebooks." Proceedings of the Speech Processing Workshop, Magdeburg Ed. Wendemuth A., -: -, 2003. 9-16.

BibTeX: 

Zuletzt aktualisiert 2018-08-08 um 22:39