2019icas--Cross-lingual Voice Conversion with Bilingual Phonetic PosteriorGram and Average Modeling
作者： Yizhou , HaizhouLi 單位：新加坡國立 & 南洋理工 abstract 用兩個單獨的語音識別系統訓練雙語的PPGs,conversion model學習雙語PPGs的關係以及對應的聲學特徵，爲了減少不同語種下說話者的干擾，從source和target 中挑選多個說話者作爲對象訓練average model（訓練asr or conversion？？ ）。I-vector作
相關文章
- 1. Odessey2018:Average Modeling Approach to Voice Conversion with Non-Parallel Data
- 2. Many-to-many Cross-lingual Voice Conversion with a Jointly Trained Speaker Embedding Network
- 3. 2019trans--Sequence-to-Sequence Acoustic Modeling for Voice Conversion
- 4. SINGING VOICE CONVERSION WITH NON-PARALLEL DATA
- 5. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
- 6. ONE-SHOT VOICE CONVERSION USING STAR-GAN
- 7. StarGAN-VC： non-parallel many-to-many voice conversion with StaGAN
- 8. 2016 ICME:Phonetic posteriorgrams for many-to-one voice conversion without parallel data training
- 9. 2018ins--Wavelet Analysis of Speaker Dependent and Independent Prosody for Voice Conversion
- 10. （ICASSP 18）Temporal Modeling Using Dilated Convolution and Gating for Voice-Activity-Detection
- 更多相關文章...
- • XSL-FO table-and-caption 對象 - XSL-FO 教程
- • W3C RDF and OWL 活動 - W3C 教程
- • RxJava操作符（七）Conditional and Boolean
- • Java 8 Stream 教程
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. Odessey2018:Average Modeling Approach to Voice Conversion with Non-Parallel Data
- 2. Many-to-many Cross-lingual Voice Conversion with a Jointly Trained Speaker Embedding Network
- 3. 2019trans--Sequence-to-Sequence Acoustic Modeling for Voice Conversion
- 4. SINGING VOICE CONVERSION WITH NON-PARALLEL DATA
- 5. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
- 6. ONE-SHOT VOICE CONVERSION USING STAR-GAN
- 7. StarGAN-VC： non-parallel many-to-many voice conversion with StaGAN
- 8. 2016 ICME:Phonetic posteriorgrams for many-to-one voice conversion without parallel data training
- 9. 2018ins--Wavelet Analysis of Speaker Dependent and Independent Prosody for Voice Conversion
- 10. （ICASSP 18）Temporal Modeling Using Dilated Convolution and Gating for Voice-Activity-Detection