Abstract | ||
---|---|---|
In the literature, a number of approaches have been proposed for learning grapheme-to-phoneme (G2P) relationship and inferring pronunciations. In this letter, we present a novel multistream framework for G2P conversion, where various machine learning techniques providing different estimates of probability of phonemes given graphemes can be effectively combined during pronunciation inference. More ... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/LSP.2017.2671451 | IEEE Signal Processing Letters |
Keywords | Field | DocType |
Hidden Markov models,Acoustics,Training,Estimation,Context,Decision trees,Probabilistic logic | Pattern recognition,Computer science,Markov model,Speech recognition,Artificial intelligence | Journal |
Volume | Issue | ISSN |
24 | 4 | 1070-9908 |
Citations | PageRank | References |
0 | 0.34 | 17 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marzieh Razavi | 1 | 30 | 4.12 |
Mathew Magimai-Doss | 2 | 516 | 54.76 |