Name
Title | ||
|---|---|---|
Recurrent Neural Network Language Model Adaptation for Multi-Genre Broadcast Speech Recognition and Alignment. |
Abstract | ||
|---|---|---|
Recurrent neural network language models (RNNLMs) generally outperform n-gram language models when used in automatic speech recognition (ASR). Adapting RNNLMs to new domains is an open problem and current approaches can be categorised as either feature-based or model based. In feature-based adaptation, the input to the RNNLM is augmented with auxiliary features whilst model-based adaptation includ... |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/TASLP.2018.2888814 | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
Adaptation models,Training,Speech recognition,Context modeling,Data models,Speech processing,Task analysis | Perplexity,Data modeling,Speech processing,Computer science,Word error rate,Recurrent neural network,Context model,Speech recognition,Language model,Test set | Journal |
Volume | Issue | ISSN |
27 | 3 | 2329-9290 |
Citations | PageRank | References |
1 | 0.37 | 11 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Salil Deena | 1 | 27 | 3.61 |
| Madina Hasan | 2 | 13 | 5.35 |
| Mortaza Doulaty | 3 | 33 | 5.35 |
| Oscar Saz | 4 | 142 | 16.30 |
| Thomas Hain | 5 | 18 | 4.50 |