FMPE: Discriminatively trained features for speech recognition

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

Volumn I, Issue , 2005, Pages

  Povey, Daniel ^a   Kingsbury, Brian ^a   Mangu, Lidia ^a   Saon, George ^a   Soltau, Hagen ^a   Zweig, Geoffrey ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DATA REDUCTION; ERROR ANALYSIS; MARKOV PROCESSES; MATHEMATICAL TECHNIQUES; MATRIX ALGEBRA;

ACOUSTIC MODEL; MINIMUM PHONE ERROR (MPE); NORMAL SIZE FEATURE SPACE;

SPEECH RECOGNITION;

EID: 33646788786     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2005.1415275     Document Type: Conference Paper

References (4)

1. Povey D. and Woodland P.C., "Minimum Phone Error and I-smoothing for Improved Discriminative Training," in ICASSP, 2002.
2. D. Povey, Discriminative Training for Large Voculabulary Speech Recognition, Ph.D. thesis, Cambridge University, 2004.
3. Saon G., Zweig G., Kingsbury B., Mangu L., and Chaudhari U., "An Architecture for Rapid Decoding of Large Vocabulary Conversational Speech," in Eurospeech, 2002.
4. Soltau H., Kingsbury B., Mangu L., Povey D., Saon G., and Zweig G., "The IBM 2004 Conversational Telephony System for Rich Transcription in EARS," in ICASSP, 2005.