Rescoring effectiveness of language models using different levels of knowledge and their integration

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

Volumn 1, Issue , 2002, Pages

  Wang, Wen ^a   Liu, Yang ^a   Harper, Mary P ^a  

^a PURDUE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

LEXICAL FEATURE; PART OF SPEECH; PERPLEXITY; RESCORING WORD GRAPHS; WORD ERROR RATE;

COMPUTATIONAL COMPLEXITY; CONTINUOUS SPEECH RECOGNITION; INTERPOLATION; MATHEMATICAL MODELS; PROBABILITY; SPEECH; SYNTACTICS;

LINGUISTICS;

EID: 0036299179     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. What is the minimal set of fragments that achieves maximal parse accuracy?
2. Immediate-head parsing for language models
3. An empirical study of smoothing techniques for language modeling
4. Extensions to constraint dependency parsing for spoken language processing
5. Effectiveness of corpus-induced dependency grammars for post-processing speech
6. POS tagging versus classes in language modeling
7. Self-organized language modeling for speech recognition
8. A variable-length category-based n-gram language model
9. Combining knowledge sources to reorder N-best speech hypothesis lists
10. Almost parsing' technique for language modeling
11. An efficient probabilistic context-free parsing algorithm that computes prefix probabilities
12. A second-order hidden Markov model for part-of-speech tagging
13. Investigating probabilistic constraint dependency grammars in language modeling