Abstract | ||
---|---|---|
The acoustic model trained using the knowledge from the shared hidden layer (SHL) model outperforms the model trained only by using the target language, especially under low resource conditions. However, the shared features may contain some unnecessary language dependent information. It will degrade the performance of the target model. Therefore, this paper proposes language-adversarial transfer l... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TASLP.2018.2889606 | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
Training,Learning systems,Speech recognition,Acoustics,Adaptation models,Neural networks,Knowledge transfer | More language,Computer science,Knowledge transfer,Transfer of learning,Word error rate,Speech recognition,Invariant (mathematics),Artificial neural network,Acoustic model,Adversarial system | Journal |
Volume | Issue | ISSN |
27 | 3 | 2329-9290 |
Citations | PageRank | References |
3 | 0.39 | 7 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiangyan Yi | 1 | 19 | 17.99 |
Jianhua Tao | 2 | 848 | 138.00 |
Zhengqi Wen | 3 | 86 | 24.41 |
Ye Bai | 4 | 7 | 5.52 |