THE DISTANCE SET REPRESENTATION OF SPEECH SEGMENTS

4th European Conference on Speech Communication and Technology, EUROSPEECH 1995

Volumn , Issue , 1995, Pages 1427-1430

  Sarukkai, Ramesh R ^a   Ballard, Dana H ^a  

^a UNIVERSITY OF ROCHESTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH COMMUNICATION;

CODEBOOKS; DISCRIMINATIVE ABILITY; DISTANCE SET; EUCLIDEAN DISTANCE; GAUSSIAN PROBABILITY DISTRIBUTIONS; MULTI-SETS; NONSEQUENTIAL; PRESENCE-ABSENCE; SET REPRESENTATION; SPEECH SEGMENTS;

PROBABILITY DISTRIBUTIONS;

EID: 33747400007     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. "Phonetic Set Hashing: A Novel Scheme for Transforming Phone Sequences to Words",Ramesh R. Sarukkai, and Dana H. Ballard, URCSTR 538, Dept. of Computer Science, Uiiiv. of Rochester, 1994.
2. "Wordspotting by Phonetic Set Indexing with Multi-layered Feedforward Networks", Ramesh R. Sarukkai, and Dana H. Ballard, submitted 1995.
3. "Experiments in Isolated Digit Recognition with a Cochlear Model", Eric P. Loeb, and Richard F. Lyon, Proc. of IEEE ICASSP '87"
4. Kai-Fu Lee, Automatic,Speech Recognition: The Development of the SPHINX.. System,,. Kluwer Academic Publishers, 1989.
5. Michael D. Riley, "Speech Time-Frequency Representations", Michael D. Riley, Kluwer Academic Pubhshers, 1989.
6. Robert M. Gray, "Vector Quantization", in in Readings in Speech Recognition, Eds. Alex Waibel, & Kai-Fu Lee, Morgan Kauffmann Inc., 1990
7. "LVQ PAK: The Learning Vector Quantization Program Package", Teuvo Kohonen et al, Helsinki Univ. of Technology,. 1992.
8. "Time-Varying Feature Selection and Classification of Unvoiced Stop Consonants", Krishna S. Nathan, and Harvey F. Silverman, IEEE Trans, on Speech and Audio Processing, Vol. 2 No. 3, July 1994.