An optimized multi-duration HMM for spontaneous speech recognition

EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology

Volumn , Issue , 2003, Pages 485-488

  Ohkawa, Yuichi ^a   Yoshida, Akihiro ^a   Suzuki, Motoyuki ^a   Ito, Akinori ^a   Makino, Shozo ^a  

^a TOHOKU UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH; SPEECH COMMUNICATION;

PARALLEL PATH; PHONEME RECOGNITION; RECOGNITION ACCURACY; SPEECH STYLE; SPEED CHANGE; SPONTANEOUS SPEECH; SPONTANEOUS SPEECH RECOGNITION; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 85009227728     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. K.Okuda, T.Kawahara, and S.Nakamura, "Speaking rate compensation based on likelihood criterion in acoustic model training and decoding", Proc. ICSLP, pp.2589-2592, 2002.
2. H.Nanjo and T.Kawahara, "Speaking-rate dependent decoding and adaptation for spontaneous lecture speech recognition", Proc. IEEE-ICASSP, pp.725-728, 2002.
3. A. Lee, Y. Mera, K. Shikano, H. Saruwatari, "Selective multi-path acoustic model based on database likelihoods", Proc. ICSLP, FrB59p.10, 2002.
4. T. Kawahara, et al.,"Free Software Toolkit for Japanese large vocabulary continuous speech recognition",Proc. ICSLP, pp.476-479, 2000.