TRANSFORMER-TRANSDUCER:END-TO-END SPEECH RECOGNITION WITH SELF-ATTENTION

时间 2021-01-11

标签语音识别asr 深度学习繁體版

原文原文链接

TRANSFORMER-TRANSDUCER:END-TO-END SPEECH RECOGNITION WITH SELF-ATTENTION 1.论文摘要（1）使用VGGNet 的因果卷积结合位置信息来对输入进行下采样来保证推理的效率。（2）使用截断自注意力机制来保证transormer的流式处理从而减少计算复杂度。取得了在LibriSPeech test-clean 6.37%的字错率，在

>>阅读原文<<

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
更多相关文章...
• XSLT 元素 - XSLT 教程
• XSL-FO page-number 对象 - XSL-FO 教程
• 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解
• 算法总结-股票买卖

最新文章

1. No provider available from registry 127.0.0.1:2181 for service com.ddbuy.ser 解决方法
2. Qt5.7以上调用虚拟键盘(支持中文)，以及源码修改(可拖动，水平缩放)
3. 软件测试面试- 购物车功能测试用例设计
4. ElasticSearch（概念篇）：你知道的, 为了搜索…
5. redux理解
6. gitee创建第一个项目
7. 支持向量机之硬间隔（一步步推导，通俗易懂）
8. Mysql 异步复制延迟的原因及解决方案
9. 如何在运行SEPM配置向导时将不可认的复杂数据库密码改为简单密码
10. windows系统下tftp服务器使用

本站公众号

欢迎关注本站公众号,获取更多信息

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

>>更多相关文章<<