Deep Belief Neural Networks and Bidirectional Long-Short Term Memory Hybrid for Speech Recognition
This paper describes a Deep Belief Neural Network (DBNN) and Bidirectional Long-Short Term Memory (LSTM) hybrid used as an acoustic model for Speech Recognition. It was demonstrated by many independent researchers that DBNNs exhibit superior performance to other known machine learning frameworks in...
保存先:
| 主要な著者: | , |
|---|---|
| フォーマット: | 論文 |
| 言語: | 英語 |
| 出版事項: |
Institute of Fundamental Technological Research Polish Academy of Sciences
2015-02-01
|
| シリーズ: | Archives of Acoustics |
| 主題: | |
| オンライン･アクセス: | https://acoustics.ippt.pan.pl/index.php/aa/article/view/1445 |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
このレコードへの初めてのコメントを付けませんか!