Data-driven approach to designing compound words for continuous speech recognition

IEEE Transactions on Speech and Audio Processing

Volumn 9, Issue 4, 2001, Pages 327-332

  Saon, George ^b   Padmanabhan, Mukund ^a,b  

^a IEEE

^b IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC SIGNAL PROCESSING; LINGUISTICS; PROBABILITY DISTRIBUTIONS; VOCABULARY CONTROL;

COMPOUND WORDS;

SPEECH RECOGNITION;

EID: 0035340902     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.917678     Document Type: Article

References (12)

1. Language modeling based on automatic word concatenations
2. Class-based n-gram models of natural language
3. Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition
4. Flexible transcription alignment
5. Word juncture modeling using phonological rules for HMM-based continuous speech recognition
6. Phrase bigrams for continuous speech recognition
7. Statistical methods for speech recognition
8. Phrase-based language models for speech recognition
9. Recent improvements in voicemail transcription
10. Class phrase models for language modeling
11. Toward better language models for spontaneous speech
12. Variable-length sequence language models for large vocabulary continuous dictation machine