Title | ||
---|---|---|
Speaker-Adapted Confidence Measures for ASR Using Deep Bidirectional Recurrent Neural Networks. |
Abstract | ||
---|---|---|
In the last years, deep bidirectional recurrent neural networks (DBRNN) and DBRNN with long short-term memory cells (DBLSTM) have outperformed the most accurate classifiers for confidence estimation in automatic speech recognition. At the same time, we have recently shown that speaker adaptation of confidence measures using DBLSTM yields significant improvements over non-adapted confidence measure... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TASLP.2018.2819900 | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
Speech,Adaptation models,Computer architecture,Training,Recurrent neural networks,Speech processing,Task analysis | Speech corpus,Speech processing,Confidence measures,Task analysis,Computer science,Long short term memory,Recurrent neural network,Speech recognition,Speaker adaptation | Journal |
Volume | Issue | ISSN |
26 | 7 | 2329-9290 |
Citations | PageRank | References |
2 | 0.40 | 26 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Miguel A. del Agua | 1 | 8 | 1.54 |
Adrià Giménez | 2 | 22 | 4.33 |
Alberto Sanchis | 3 | 24 | 4.40 |
Jorge Civera | 4 | 243 | 27.87 |
alfons juan | 5 | 572 | 61.45 |