Abstract | ||
---|---|---|
The study of a system for Vietnamese continuous digit recognition is described. The CSLU Toolkit was used to develop and implement hybrid HMM/ANN recognition systems. Experiments were done with a corpus of 442 sentences with 2340 words, which were extracted from two telephone-speech corpora: "22 Language v1.2" and "Multi-Language Telephone Speech v1.2". In our experiments, a context-dependent phoneme recognizer has achieved better recognition performance than a context-dependent demi-syllable recognizer and a context-independent phoneme recognizer. Among feature sets applied to the context-dependent phoneme recognizer, the set of 12 PLP features with CMS, energy and corresponding delta values has achieved the best recognition result (96.83% word accuracy and 87.67% sentence correct). |
Year | DOI | Venue |
---|---|---|
2003 | 10.1007/3-540-45034-3_48 | international conference on supercomputing |
Keywords | Field | DocType |
context-dependent phoneme recognizer,ANN recognition system,Vietnamese continuous digit recognition,best recognition result,better recognition performance,context-dependent demi-syllable recognizer,context-independent phoneme recognizer,Multi-Language Telephone Speech v1,language v1,CSLU Toolkit,ANN system,vietnamese continuous digit recognition | Computer science,Markov model,Phrase,Speech recognition,Natural language processing,Syllable,Artificial intelligence,Digit recognition,Vietnamese,Artificial neural network,Hidden Markov model,Sentence | Conference |
Volume | ISSN | ISBN |
2718 | 0302-9743 | 3-540-40455-4 |
Citations | PageRank | References |
2 | 0.40 | 2 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dang Ngoc Duc | 1 | 2 | 0.40 |
John-Paul Hosom | 2 | 231 | 23.43 |
Luong Chi Mai | 3 | 22 | 4.54 |
Thang Vu Tat | 4 | 2 | 0.40 |