TRANSFORMER-TRANSDUCER:END-TO-END SPEECH RECOGNITION WITH SELF-ATTENTION
TRANSFORMER-TRANSDUCER:END-TO-END SPEECH RECOGNITION WITH SELF-ATTENTION 1.論文摘要 （1）使用VGGNet 的因果卷積結合位置信息來對輸入進行下采樣來保證推理的效率。（2）使用截斷自注意力機制來保證transormer的流式處理從而減少計算複雜度。取得了在LibriSPeech test-clean 6.37%的字錯率，在
相關文章
- 1. Food Log with Speech Recognition and NLP
- 2. (7) [IEEEAcoustic13] SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS
- 3. 文章：Emotion Recognition From Speech With Recurrent Neural Networks
- 4. Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions
- 5. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
- 6. speech recognition resource
- 7. Almost Unsupervised Text to Speech and Automatic Speech Recognition
- 8. Interspeech 2017 | Far-field Speech Recognition Technology
- 9. Interspeech 2017 | Self-adaptive Speech Recognition Technology
- 10. 5 Open Source Speech Recognition/Speech-to-Text Systems
- 更多相關文章...
- • XSLT
- • XSL-FO page-number 對象 - XSL-FO 教程
- • 爲了進字節跳動，我精選了29道Java經典算法題，帶詳細講解
- • 算法總結-股票買賣
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. Food Log with Speech Recognition and NLP
- 2. (7) [IEEEAcoustic13] SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS
- 3. 文章：Emotion Recognition From Speech With Recurrent Neural Networks
- 4. Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions
- 5. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
- 6. speech recognition resource
- 7. Almost Unsupervised Text to Speech and Automatic Speech Recognition
- 8. Interspeech 2017 | Far-field Speech Recognition Technology
- 9. Interspeech 2017 | Self-adaptive Speech Recognition Technology
- 10. 5 Open Source Speech Recognition/Speech-to-Text Systems