Abstract | ||
---|---|---|
We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the dimensions of phonetics, phonology, language family, geographical location, and orthography. In this context, experiments demonstrate the effectiveness of two additional pretraining objectives in encouraging language-independent encoder representations: a context-independent phoneme objective paired with a language-adversarial classification objective. |
Year | DOI | Venue |
---|---|---|
2019 | 10.18653/v1/n19-1009 | North American Chapter of the Association for Computational Linguistics |
Field | DocType | Volume |
Computer science,Phonetics,Speech recognition,Orthography,Natural language processing,Encoder,Artificial intelligence,Phonology,Language family,Adversarial system | Journal | abs/1904.02210 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Oliver Adams | 1 | 0 | 0.68 |
Matthew Wiesner | 2 | 5 | 2.85 |
Shinji Watanabe | 3 | 1158 | 139.38 |
David Yarowsky | 4 | 2 | 3.42 |