DocumentCode :
699749
Title :
Overcoming HMM time independence assumption using N-gram based modelling for continuous speech recognition
Author :
Casar, Marta ; Fonollosa, Jose A. R.
Author_Institution :
Dept. of Signal Theor. & Commun., Univ. Politec. de Catalunya, Barcelona, Spain
fYear :
2008
fDate :
25-29 Aug. 2008
Firstpage :
1
Lastpage :
5
Abstract :
The development of new acoustical models that overcome traditional HMM restrictions is an active field of research in automatic speech recognition. One possible approach to achieve this goal is to work with N-gram based augmented HMM. In this paper, we propose to deal with time independence assumption of HMM using N-gram based modelling. For this, the temporal dependencies of each acoustic feature are explicitly modelled. Results obtained in this work testing this approach in continuous speech recognition show the suitability of adding long span information for ASR performance. Moreover, we are improving previous results obtained using this modelling scheme in connected digit recognition experiments.
Keywords :
hidden Markov models; speech recognition; HMM time independence assumption; N-gram based modelling; automatic speech recognition; continuous speech recognition; hidden Markov model; Acoustics; Computational modeling; Databases; Hidden Markov models; Speech; Speech recognition; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Conference, 2008 16th European
Conference_Location :
Lausanne
ISSN :
2219-5491
Type :
conf
Filename :
7080281
Link To Document :
بازگشت