Abstract | ||
---|---|---|
The paper addresses manual and semi-automatic approaches to building a multilingual phoneme set for automatic speech recognition. The first approach involves mapping and reduction of the phoneme set based on IPA and expert knowledge, the later one involves phoneme confusion matrix generated by a neural network. The comparison is done for 8 languages selected from GlobalPhone on three scenarios: 1) multilingual system with abundant data for all the languages, 2) multilingual systems excluding target language 3) multilingual systems with small amount of data for target languages. For 3), the multilingual system brought improvement for languages close enough to the others in the set. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICASSP.2013.6639085 | ICASSP |
Keywords | Field | DocType |
neural network,expert systems,speech recognition,semiautomatic multilingual phoneme set building,expert knowledge,multilingual speech recognition,natural language processing,manual multilingual phoneme set building,ipa,phoneme confusion matrix,phoneme set mapping,neural nets,automatic speech recognition,multilingual system,hidden markov models,acoustics,speech | Confusion matrix,Computer science,Expert system,Speech recognition,Artificial intelligence,Natural language processing,Artificial neural network | Conference |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
1 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ekaterina Egorova | 1 | 17 | 4.04 |
Karel Veselý | 2 | 154 | 14.62 |
Martin Karafiát | 3 | 176 | 10.92 |
Milos Janda | 4 | 18 | 2.06 |
Jan Cernocký | 5 | 1273 | 135.94 |