2018ins--Wavelet Analysis of Speaker Dependent and Independent Prosody for Voice Conversion
單位：新加坡國立 作者：Haizhou Li abstract 現在的vc基本都是基於譜做的變換，但是和說話者相關的韻律特徵，比如基頻、能量包絡，我們認爲如果能量更好的理解基頻，就能更好的實現更好的vc效果。說話者依賴的特徵是說話者的特性，說話者獨立的特徵是語言表達的特性，在vc任務中，前者是需要轉換的，後者是需要保留的。我們提出用wavelet在不同的時間尺度分析這兩個特徵。 （譜參數與音色有
相關文章
- 1. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
- 2. Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification
- 3. 2019trans--Sequence-to-Sequence Acoustic Modeling for Voice Conversion
- 4. 2019icas--Cross-lingual Voice Conversion with Bilingual Phonetic PosteriorGram and Average Modeling
- 5. Whether To Pretrain DNN or Not?: An Empirical Analysis for Voice Conversion
- 6. Many-to-many Cross-lingual Voice Conversion with a Jointly Trained Speaker Embedding Network
- 7. 2016 ICME:Phonetic posteriorgrams for many-to-one voice conversion without parallel data training
- 8. Voice Conversion Across Arbitrary Speakers based on a Single Target-Speaker Utterance
- 9. x-vector：Deep Neural Network Embeddings for Text-Independent Speaker Verification
- 10. ONE-SHOT VOICE CONVERSION USING STAR-GAN
- 更多相關文章...
- • Scala for循環 - Scala教程
- • Swift for 循環 - Swift 教程
- • RxJava操作符（七）Conditional and Boolean
- • Flink 數據傳輸及反壓詳解
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。
最新文章
- 1. js中 charCodeAt
- 2. Android中通過ViewHelper.setTranslationY實現View移動控制（NineOldAndroids開源項目）
- 3. 【Android】日常記錄：BottomNavigationView自定義樣式，修改點擊後圖片
- 4. maya 文件檢查 ui和數據分離 （一）
- 5. eclipse 修改項目的jdk版本
- 6. Android InputMethod設置
- 7. Simulink中Bus Selector出現很多? ? ?
- 8. 【Openfire筆記】啓動Mac版Openfire時提示「系統偏好設置錯誤」
- 9. AutoPLP在偏好標籤中的生產與應用
- 10. 數據庫關閉的四種方式
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
- 2. Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification
- 3. 2019trans--Sequence-to-Sequence Acoustic Modeling for Voice Conversion
- 4. 2019icas--Cross-lingual Voice Conversion with Bilingual Phonetic PosteriorGram and Average Modeling
- 5. Whether To Pretrain DNN or Not?: An Empirical Analysis for Voice Conversion
- 6. Many-to-many Cross-lingual Voice Conversion with a Jointly Trained Speaker Embedding Network
- 7. 2016 ICME:Phonetic posteriorgrams for many-to-one voice conversion without parallel data training
- 8. Voice Conversion Across Arbitrary Speakers based on a Single Target-Speaker Utterance
- 9. x-vector：Deep Neural Network Embeddings for Text-Independent Speaker Verification
- 10. ONE-SHOT VOICE CONVERSION USING STAR-GAN