Hierarchical Generative Modeling for Controllable Speech Synthesis筆記
文章目錄 可控語音合成的分層生成建模 一、簡介 二、模型 2.1 具有分層隱式變量的可控生成模型 2.2 變分推論和訓練 2.3 顯示分類標籤的連續屬性空間 2.4 神經網絡結構 三、相關研究 四、實驗 可控語音合成的分層生成建模 本文提出了一種神經端到端文本到語音（TTS）模型，該模型可以控制生成的語音中潛在的屬性，這些屬性很少在訓練數據中註釋，例如說話風格，重音，背景噪聲和記錄條件。該模型被公
相關文章
- 1. Waveform Modeling and Generation Using Hierarchical Recurrent Neural Networks for Speech Bandwidth E...
- 2. Uncovering Latent Style Factors for Expressive Speech Synthesis
- 3. Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
- 4. Hierarchical Attention Network for Document Classification閱讀筆記
- 5. 《A Review of Unsupervised Feature Learning and Deep Learning for Time-Series Modeling》筆記
- 6. Tacotron: Towards End-to-End Speech Synthesis
- 7. Generative Adversarial Text to Image Synthesis
- 8. Controllable Multi-Interest Framework for Recommendation
- 9. FastSpeech: Fast, Robust and Controllable Text to Speech
- 10. Transformer-TTS: Neural Speech Synthesis with Transformer Network閱讀筆記
- 更多相關文章...
- • ASP.NET Razor - 標記 - ASP.NET 教程
- • Scala for循環 - Scala教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • 算法總結-滑動窗口
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. Waveform Modeling and Generation Using Hierarchical Recurrent Neural Networks for Speech Bandwidth E...
- 2. Uncovering Latent Style Factors for Expressive Speech Synthesis
- 3. Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
- 4. Hierarchical Attention Network for Document Classification閱讀筆記
- 5. 《A Review of Unsupervised Feature Learning and Deep Learning for Time-Series Modeling》筆記
- 6. Tacotron: Towards End-to-End Speech Synthesis
- 7. Generative Adversarial Text to Image Synthesis
- 8. Controllable Multi-Interest Framework for Recommendation
- 9. FastSpeech: Fast, Robust and Controllable Text to Speech
- 10. Transformer-TTS: Neural Speech Synthesis with Transformer Network閱讀筆記