Bayesian neural network language modeling for speech recognition
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when given limited training data. To this end, an overarching full B...
Saved in:
Main Authors: | , , , , , |
---|---|
其他作者: | |
格式: | Article |
語言: | English |
出版: |
2023
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/164438 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|