Using quick transcriptions to improve conversational speech models

8th International Conference on Spoken Language Processing, ICSLP 2004

Volumn , Issue , 2004, Pages 2265-2268

  Kimball, Owen ^a   Kao, Chia Lin ^a   Iyer, Rukmini ^b   Arvizo, Teodoro ^a   Makhoul, John ^a  

^a BBN TECHNOLOGIES   (United States)

^b NUANCE COMMUNICATIONS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

TRANSCRIPTION;

COLLECTION EFFORT; CONVERSATIONAL SPEECH; CONVERSATIONAL SPEECH RECOGNITION; LARGE CORPORA; SEGMENTATION ALGORITHMS; STATE OF THE ART; TIMING INFORMATION; TRANSCRIPTION METHODS;

SPEECH RECOGNITION;

EID: 84893372402     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. C. Cieri, D. Miller, and K. Walker, "From Switchboard to Fisher: telephone collection protocols, theirs uses and yields", Proc. Eurospeech, Switzerland, pp 1597-1600, 2003.
2. G. Zavaliagkos and T. Colthurst, "Utilizing untranscribed training data to improve performance," in Proc. DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, VA, pp. 301-305, 1998.
3. L. Lamel, J.-L. Gauvain, and G. Adda, "Unsupervised acoustic model training," in Proc. ICASSP, pp. 877-880, IEEE, 2002.
4. A. Gunawardana and A. Acero, "Adapting Acoustic Models to New Domains and Conditions Using Untranscribed Data," in Proc. Eurospeech, Switzerland, pp. 1633-1636, 2003.
5. J. Hamaker, Y. Zeng, and J. Picone, "Rules and Guidelines for Transcription and Segmentation of the SWITCHBOARD Large Vocabulary Conversational Speech Recognition Corpus", http://www.isip.msstate.edu/projects/switchboard/doc/transcription-guidelines/transcription-guidelines.pdf, 1998.
6. J. Godfrey, E. Holliman, and J. McDaniel, "SWITCHBOARD: Telephone speech corpus for research and development," Proc. ICASSP'92, pp. 517-520, 1992.
7. R. Schwartz et al, "Speech recognition in multiple languages and domains: The BBN/LIMSI EARS system", to appear in Proc. ICASSP, Montreal, Canada, May, 2004.
8. R. Iyer, "Relevance Weighting for Combining MultiDomain Data for N-Gram Language Modeling", Computer Speech and Language, vol. 13, No. 3, pp. 267-282, 1999.