Text normalization with varied data sources for conversational speech language modeling

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

Volumn 1, Issue , 2002, Pages

  Schwarm, Sarah ^a   Ostendorf, Mari ^a  

^a University of Washington   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

MATHEMATICAL MODELS; SPEECH; SPEECH RECOGNITION; SPEECH SYNTHESIS;

DATA SOURCES; LINGUISTIC DATA CONSORTIUM; TEXT NORMALIZATION; WORD ERROR RATE;

LINGUISTICS;

EID: 17444438596     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/icassp.2002.5743836     Document Type: Conference Paper

References (10)

1. The meeting project at ICSI
2. Optimizing lexical and n-gram coverage via judicious use of linguistic data
3. Relevance weighting for combining multi-domain data for n-gram language modeling
4. Experiments in adaptation of language models for commercial applications
5. Transforming out-of-domain estimates to improve in-domain language models
6. The IBM large vocabulary continuous speech recognition system for the ARPA NAB news task
7. The SRI March 2000 hub-5 conversational speech transcription system
8. Linguistic data consortium
9. Normalization of non-standard words