A new phonetic tied-mixture model for efficient decoding

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

Volumn 3, Issue , 2000, Pages 1269-1272

  Lee, Akinobu ^a   Kawahara, Tatsuya ^a   Takeda, Kazuya ^b   Shikano, Kiyohiro ^c  

^a KYOTO UNIVERSITY   (Japan)

^b NAGOYA UNIVERSITY   (Japan)

^c NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; DECODING; LINGUISTICS; MIXTURES; SIGNAL PROCESSING; SPEECH PROCESSING; ESTIMATION; MARKOV PROCESSES; MATHEMATICAL MODELS; NORMAL DISTRIBUTION; OPTIMIZATION; SPEECH ANALYSIS; SPEECH RECOGNITION; VOCABULARY CONTROL;

CONTEXT INDEPENDENT; HIGHER RESOLUTION; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LOSS OF ACCURACY; MIXTURE COMPONENTS; NEWSPAPER CORPUS; TIED-MIXTURES; WORD ERROR RATE;

SPEECH RECOGNITION; ACOUSTIC SIGNAL PROCESSING;

GAUSSIAN PRUNING; HIDDEN MARKOV MODEL; PHONETIC TIED MIXTURE MODEL; WORD ERROR RATE;

EID: 0033721605     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.861808     Document Type: Conference Paper

References (5)

1. G. Zavaliagkos, J. McDonough, D. Miller, A. El-Jaroudi, J. Billa, F. Richardson, K. Ma, M. Siu, H. Gish: The BBN BYBLOS 1997 Large Vocabulary Conversational Speech Recognition System, In IEEE ICASSP, pages 905-908, 1998.
2. A. Sankar: A New Look at HMM Parameter Tying for Large Vocabulary Speech Recognition, In Proc. ICSLP, pages 2219-2222, 1998.
3. A. Lee, T. Kawahara, S. Doshita: An Efficient Two-Pass Search Algorithm using Word Trellis Index, In Proc. ICSLP, pages 1831-1834, 1998.
4. T. Kawahara, T. Kobayashi, K. Takeda, N. Minematsu, K. Itou, M. Yamamoto, A. Tamada, T. Utsuro and K. Shikano: Sharable Software Repository for Japanese Large Vocabulary Continuous Speech Recognition, In Proc. ICSLP, 1998.
5. K. Itou, M. Yamamoto, K. Takeda, T. Takezawa, T. Matsuoka, T. Kobayashi, K. Shikano and S. Itahashi: The Design of the Newspaper-Based Japanese Large Vocabulary Continuous Speech Recognition Corpus, In Proc. ICSLP 1998.