Combined use of speaker-and tone-normalized pitch reset with pause duration for automatic story segmentation in Mandarin broadcast news

NAACL-HLT 2007 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Companion Volume: Short Papers

Volumn , Issue , 2007, Pages 193-196

  Xie, Lei ^a   Liu, Chuan ^a   Meng, Helen ^a  

^a CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; SEMANTICS;

BOUNDARY DETECTION; BROADCAST NEWS; F MEASURE; MANDARIN CHINESE; STORY SEGMENTATION;

DECISION TREES;

EID: 85089104276     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Shriberg E., Stolcke A., Hakkani-Tür D. and Tür G. 2000. Prosody-based automatic segmentation of speech into sentences and topics. Speech Comm., 32(1-2):127-154.
2. Tür G. and Hakkani-Tür D. 2001. Integrating Prosodic and Lexical Cues for Automatic Topic Segmentation. Computational Linguistics, 27(1):31-57.
3. Levow G. A. 2004. Prosody-based Topic Segmentation for Mandarin Broadcast News. Proc. of HLT-NAACL, 137-140.
4. The Linguistic Data Consortium. 1998. http://projects.ldc.upenn.edu/TDT2/.
5. de Cheveignë A. and Kawahara H. 2002. Yin, a fundamental frequency estimator for speech and music. Journal of the Acoustic Society of America, 111(4):1917-1930.
6. Tseng C. Y., Pin S. H., Lee Y., Wang H. M. and Chen Y. C. 2005. Fluent speech prosody: Framework and modeling. Speech Comm., 46:284-309.
7. Quinlan J. R. 1992. C4.5: Programs for Machine Learning. Morgan Kaufmann.