Transformer-TTS: Neural Speech Synthesis with Transformer Network阅读笔记

时间 2020-12-29

标签语音合成TTS Transformer transformer-TTS attention end2end TTS 语音合成栏目系统网络繁體版

原文原文链接

5. Transformer-TTS: Neural Speech Synthesis with Transformer Network 文章于2019年1月发表 Transformer-TTS可以看做Tacotron2+transformer的组合，作者认为优点主要为：通过移除RNN结构实现并行训练，因为解码器的输入序列的帧可以并行地提供。第二种是self-attention可以将整个序列的

>>阅读原文<<

1. 《Video Action Transformer Network》阅读笔记（附Transformer的笔记内容）
2. 论文《Chinese Poetry Generation with Recurrent Neural Network》阅读笔记
3. 【论文阅读笔记】Deep Neural Network Compression with Single and Multiple Level Quantization
4. Document Modeling with Gated Recurrent Neural Network for Sentiment Classification 论文阅读笔记
5. 论文阅读笔记（一）——Deep Convolutional Neural Network with Independent
6. 【论文阅读笔记】Document Modeling with Gated Recurrent Neural Network for Sentiment Classification
7. 《Reasoning about Entailment with Neural Attention》阅读笔记
8. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
9. 论文阅读：Spatial Transformer Network
10. 阅读笔记 CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network
更多相关文章...
• RSS 阅读器 - RSS 教程
• PHP 实例 - AJAX RSS 阅读器 - PHP教程
• Tomcat学习笔记（史上最全tomcat学习笔记）
• JDK13 GA发布：5大特性解读

最新文章

1. IDEA 2019.2解读：性能更好，体验更优！
2. 使用云效搭建前端代码仓库管理，构建与部署
3. Windows本地SVN服务器创建用户和版本库使用
4. Sqli-labs-Less-46（笔记）
5. Docker真正的入门
6. vue面试知识点
7. 改变jre目录之后要做的修改
8. 2019.2.23VScode的c++配置详细方法
9. 从零开始OpenCV遇到的问题一
10. 创建动画剪辑

本站公众号

欢迎关注本站公众号,获取更多信息

1. 《Video Action Transformer Network》阅读笔记（附Transformer的笔记内容）
2. 论文《Chinese Poetry Generation with Recurrent Neural Network》阅读笔记
3. 【论文阅读笔记】Deep Neural Network Compression with Single and Multiple Level Quantization
4. Document Modeling with Gated Recurrent Neural Network for Sentiment Classification 论文阅读笔记
5. 论文阅读笔记（一）——Deep Convolutional Neural Network with Independent
6. 【论文阅读笔记】Document Modeling with Gated Recurrent Neural Network for Sentiment Classification
7. 《Reasoning about Entailment with Neural Attention》阅读笔记
8. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
9. 论文阅读：Spatial Transformer Network
10. 阅读笔记 CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network

>>更多相关文章<<