Abstract | ||
---|---|---|
An automatic procedure for modeling alternative pronunciations of words produced by different talkers is described. The research compared recognition performance on forty city and state names using three different representations of each word. In the first case, the expected pronunciation(s) of each word was produced by an expert. In the second case, a dynamic programming algorithm was used to create a pronunciation network for each word by combining phonetic transcriptions from ten utterances of the word produced by human labelers. The third case was identical to the second, except that the phonetic labels were provided automatically by a phonetic recognition algorithm. On a test set of words produced by new speakers, equivalent recognition performance was observed for the pronunciation networks derived from human and machine labels. Both produced performance superior to that obtained with the pronunciations produced by the expert.<> |
Year | DOI | Venue |
---|---|---|
1993 | 10.1109/ICASSP.1993.319275 | Acoustics, Speech, and Signal Processing, 1993. ICASSP-93., 1993 IEEE International Conference |
Keywords | Field | DocType |
dynamic programming,speech recognition,dynamic programming algorithm,phoneme classifier,phonetic labels,pronunciation networks,recognition performance,word pronunciations | Pronunciation,Dynamic programming,Transcription (linguistics),Computer science,Speech recognition,Error detection and correction,Context model,Natural language,Natural language processing,Artificial intelligence,Classifier (linguistics),Test set | Conference |
Volume | ISSN | ISBN |
2 | 1520-6149 | 0-7803-0946-4 |
Citations | PageRank | References |
13 | 1.97 | 5 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Philipp Schmid | 1 | 13 | 1.97 |
Ronald A. Cole | 2 | 686 | 187.46 |
Mark Fanty | 3 | 21 | 6.22 |