Automatic acoustic segmentation for speech recognition on broadcast recordings

International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007

Volumn 4, Issue , 2007, Pages 2580-2583

  Peng, Gang ^a   Hwang, Mei Yuh ^a   Ostendorf, Mari ^a  

^a University of Washington   (United States)

Author keywords

Automatic acoustic segmentation; Broadcast conversation; Broadcast news; Machine translation; Speech recognition

Indexed keywords

ACOUSTICS; COMPUTER AIDED LANGUAGE TRANSLATION; ERRORS; IMAGE SEGMENTATION; INFORMATION THEORY; LINGUISTICS; SPEECH; SPEECH ANALYSIS; SPEECH RECOGNITION; SPEECH TRANSMISSION;

ACOUSTIC SEGMENTATIONS; AUTOMATIC ACOUSTIC SEGMENTATION; AUTOMATIC SEGMENTATIONS; BROADCAST NEWS; MACHINE TRANSLATION; MULTIPLE MODELS; PHONETIC KNOWLEDGES; SEGMENTATION ALGORITHMS; SEGMENTER; SPECIFIC KNOWLEDGES; SPEECH RECORDINGS; SPEECH SEGMENTS;

SPEECH COMMUNICATION;

EID: 56249126812     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. Hwang, M.-Y., Lei, X., Zheng, J., Cetin, O., Wang, W., Peng, G., and Stolcke, A., "Advances in Mandarin broadcast speech recognition", Interspeech 2007.
2. Povey, D., and Woodland, P.C., "Minimum phone error and I-smoothing for improved discriminative training", ICASSP 2002.
3. Zheng, J., Cetin, O., Hwang, M.-Y., Lei, X., Stolcke, A., and Norgan, N., "Combining discriminative feature, transform, and model training fro large vocabulary speech recognition", ICASSP 2007.
4. Chen, B., Zhu, Q., and Morgan, N., "Learning long-term temporal features in LVCSR using neural networks", ICSLP 2004.
5. Mangu, L., Brill, E., and Stolcke, A., "Finding consensus in speech recognition: Word error minimization and other applications of confusion networks", Computer Speech and Language, 373-400, 2000.