Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin論文筆記
感想 這篇文章的署名作者尤其的多，做了很多工作，從模型設計到產品不熟，還實現了一個GPU版本的CTC，CTC可以說是這篇文章的核心部分，沒有它，就沒有端到端的訓練，作者還用到了雙向神經網絡，對GPU並行都做了相應的定製化優化，涉及的很全，算法比較實驗也很全，大多都是很人類水平比較。 介紹 數十年的手工工程領域知識已經融入到了最新的自動語音識別（automatic speech recognitio
相關文章
- 1. Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- 2. Deep Speech筆記
- 3. 論文筆記：DEEP LEARNING FOR MONAURAL SPEECH SEPARATION
- 4. Almost Unsupervised Text to Speech and Automatic Speech Recognition
- 5. Visual Speech Recognition: Lip Segmentation and Mapping
- 6. Food Log with Speech Recognition and NLP
- 7. (7) [IEEEAcoustic13] SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS
- 8. 論文 Convolutional Networks for Images, Speech, and Time-Series
- 9. Speech recognition using deep neural network: A systematic review 論文簡述
- 10. Efficient Active Learning for Automatic Speech Recognition... 論文筆記
- 更多相關文章...
- • Swift for-in 循環 - Swift 教程
- • SQL IN 操作符 - SQL 教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • RxJava操作符（七）Conditional and Boolean
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- 2. Deep Speech筆記
- 3. 論文筆記：DEEP LEARNING FOR MONAURAL SPEECH SEPARATION
- 4. Almost Unsupervised Text to Speech and Automatic Speech Recognition
- 5. Visual Speech Recognition: Lip Segmentation and Mapping
- 6. Food Log with Speech Recognition and NLP
- 7. (7) [IEEEAcoustic13] SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS
- 8. 論文 Convolutional Networks for Images, Speech, and Time-Series
- 9. Speech recognition using deep neural network: A systematic review 論文簡述
- 10. Efficient Active Learning for Automatic Speech Recognition... 論文筆記