2016 ICME:Phonetic posteriorgrams for many-to-one voice conversion without parallel data training
作者： Helen Meng 單位：港中文 abstract 非平行訓練數據進行voice conversion 首先用一個SI-ASR（speaker-independent 語音識別系統）提取PPGs(Phonetic PosteriorGrams)，這個PPGs可以對應於說話者的發音，並且對應於獨立說話者的 說話內容。 然後用DBLSTM（deep bi-LSTM)建模PPGs和target
相關文章
- 1. SINGING VOICE CONVERSION WITH NON-PARALLEL DATA
- 2. Odessey2018:Average Modeling Approach to Voice Conversion with Non-Parallel Data
- 3. 2019trans--Sequence-to-Sequence Acoustic Modeling for Voice Conversion
- 4. StarGAN-VC： non-parallel many-to-many voice conversion with StaGAN
- 5. AdaGAN:adaptive GAN for many-to-many non-parallel voice converison
- 6. StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion
- 7. ONE-SHOT VOICE CONVERSION USING STAR-GAN
- 8. Whether To Pretrain DNN or Not?: An Empirical Analysis for Voice Conversion
- 9. Parallel-data-free voice conver- sion using cycle-consistent adversarial networks
- 10. 【每週論文】Graphene： Packing and Dependency-aware Scheduling for Data-Parallel Clusters（OSDI 2016）
- 更多相關文章...
- • Swift for 循環 - Swift 教程
- • Scala for循環 - Scala教程
- • Java 8 Stream 教程
- • 爲了進字節跳動，我精選了29道Java經典算法題，帶詳細講解
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。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. SINGING VOICE CONVERSION WITH NON-PARALLEL DATA
- 2. Odessey2018:Average Modeling Approach to Voice Conversion with Non-Parallel Data
- 3. 2019trans--Sequence-to-Sequence Acoustic Modeling for Voice Conversion
- 4. StarGAN-VC： non-parallel many-to-many voice conversion with StaGAN
- 5. AdaGAN:adaptive GAN for many-to-many non-parallel voice converison
- 6. StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion
- 7. ONE-SHOT VOICE CONVERSION USING STAR-GAN
- 8. Whether To Pretrain DNN or Not?: An Empirical Analysis for Voice Conversion
- 9. Parallel-data-free voice conver- sion using cycle-consistent adversarial networks
- 10. 【每週論文】Graphene： Packing and Dependency-aware Scheduling for Data-Parallel Clusters（OSDI 2016）