Many-to-many Cross-lingual Voice Conversion with a Jointly Trained Speaker Embedding Network
会议：2019 APSIPA 作者：ZHOUYI Li Haizhou 单位：新加坡国立 abstract average modeling approach用一个低维度的speaker embedding和vc网络联合训练，可以达到many-to-many cross-lingual的效果。 base-model: vc+i-vector作为speaker embedding表示。 introd
相关文章
- 1. Voice Conversion Across Arbitrary Speakers based on a Single Target-Speaker Utterance
- 2. SINGING VOICE CONVERSION WITH NON-PARALLEL DATA
- 3. Neural Voice Cloning with a Few Samples
- 4. ONE-SHOT VOICE CONVERSION USING STAR-GAN
- 5. 行人属性“Person Attribute Recognition with a Jointly-trained Holistic CNN Model”
- 6. X-VECTOR:ROBUST DNN EMBEDDING FOR SPEAKER RECOGNITION
- 7. 2019trans--Sequence-to-Sequence Acoustic Modeling for Voice Conversion
- 8. 2019icas--Cross-lingual Voice Conversion with Bilingual Phonetic PosteriorGram and Average Modeling
- 9. Odessey2018:Average Modeling Approach to Voice Conversion with Non-Parallel Data
- 10. 2018ins--Wavelet Analysis of Speaker Dependent and Independent Prosody for Voice Conversion
- 更多相关文章...
- • XSLT
- • XSL-FO page-number 对象 - XSL-FO 教程
- • 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解
- • Flink 数据传输及反压详解
相关标签/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
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Voice Conversion Across Arbitrary Speakers based on a Single Target-Speaker Utterance
- 2. SINGING VOICE CONVERSION WITH NON-PARALLEL DATA
- 3. Neural Voice Cloning with a Few Samples
- 4. ONE-SHOT VOICE CONVERSION USING STAR-GAN
- 5. 行人属性“Person Attribute Recognition with a Jointly-trained Holistic CNN Model”
- 6. X-VECTOR:ROBUST DNN EMBEDDING FOR SPEAKER RECOGNITION
- 7. 2019trans--Sequence-to-Sequence Acoustic Modeling for Voice Conversion
- 8. 2019icas--Cross-lingual Voice Conversion with Bilingual Phonetic PosteriorGram and Average Modeling
- 9. Odessey2018:Average Modeling Approach to Voice Conversion with Non-Parallel Data
- 10. 2018ins--Wavelet Analysis of Speaker Dependent and Independent Prosody for Voice Conversion