Acoustic modeling with contextual additive structure for HMM-based speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2008, Pages 4469-4472

  Nankaku, Yoshihiko ^a   Nakamura, Kazuhiro ^a   Zen, Heiga ^a   Tokuda, Keiichi ^a  

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Additive structure; Context clustering; Decision trees; Distribution convolution; Hidden Markov models

Indexed keywords

ACOUSTICS; CLUSTERING ALGORITHMS; DECISION MAKING; DECISION THEORY; DECISION TREES; HIDDEN MARKOV MODELS; IMAGE SEGMENTATION; LINGUISTICS; MATHEMATICAL MODELS; SIGNAL PROCESSING; SPEECH; SPEECH ANALYSIS; TREES (MATHEMATICS);

ACOUSTIC MODELLING; ADDITIVE STRUCTURE; CONTEXT CLUSTERING; DISTRIBUTION CONVOLUTION; INTERNATIONAL CONFERENCES;

PROBABILITY DISTRIBUTIONS;

EID: 51449118125     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2008.4518648     Document Type: Conference Paper

References (5)

1. J. Odell, "The Use of Context in Large Vocabulary Speech Recognition," PhD dissertation, University of Cambridge, 1995.
2. K. Shinoda and T. Watanabe, "MDL-based context-dependent subword modeling for speech recognition," J. Acoust. Soc. Jpn. (E), vol.21, no.2, pp.79-86, 2000.
3. Y. Abe and K. Nakajima "Speech Recognition Using Dynamic Transformation of Phoneme Templates Depending of Acoustic/Phonetic Environments," Proc. ICASSP'89, pp.326-329, 1992.
4. S. Matsoukas and G. Zavaliagkos, "Convolutional Density Estimation In Hidden Markov Models For Speech Recognition," Proc. ICASSP'99, pp.113-116, 1999.
5. T. Fukada, K. Tokuda, T. Kobayashi and S. Imai, "An Adaptive Algorithm for Mel-Cepstral Analysis of Speech,"Proc. ICASSP'92, vol.1,pp.137-140, 1992.