DocumentCode :
431260
Title :
Analysis of a large in-car speech corpus and its application to the multimodel ASR
Author :
Fujimua, Hiroshi ; Miyajima, Chiyomi ; Itou, Katsunobu ; Takeda, Kazuya ; Itakura, Fumitada
Author_Institution :
Graduate Sch. of Inf. Sci., Nagoya Inst. of Technol., Japan
Volume :
1
fYear :
2005
fDate :
March 18-23, 2005
Firstpage :
445
Lastpage :
448
Keywords :
entropy; hidden Markov models; regression analysis; speech recognition; HMM acoustic model; entropy; factor analysis; in-car speech corpus analysis; linear regression model; multimodel ASR; real driving condition driver utterances; speaking rate; subband SNR model selection measure; subband-SNR-dependent acoustic model; utterance duration; utterance length-dependent language model; word accuracy; Automatic speech recognition; Design methodology; Entropy; Hidden Markov models; Large-scale systems; Microphones; Speech analysis; Speech enhancement; Speech processing; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
0-7803-8874-7
Type :
conf
DOI :
10.1109/ICASSP.2005.1415146
Filename :
1415146
Link To Document :
بازگشت