ASSEM-VC: REALISTIC VOICE CONVERSION BY ASSEMBLING MODERN SPEECH SYNTHESIS TECHNIQUES

被引：9

作者：

Kim, Kang-Wook ^{[1
,2
]}

Park, Seung-Won ^{[2
]}

Lee, Junhyeok ^{[1
]}

Joe, Myun-Chul ^{[1
]}

机构：

[1] MINDsLab Inc, Seongnam Si, Gyeonggi Do, South Korea

[2] Seoul Natl Univ, Seoul, South Korea

来源：

2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2022年

关键词：

voice conversion; speech synthesis; speaker disentanglement; adversarial training;

D O I：

10.1109/ICASSP43922.2022.9746139

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Recent works on voice conversion (VC) focus on preserving the rhythm and the intonation as well as the linguistic content. To preserve these features from the source, we decompose current non-parallel VC systems into two encoders and one decoder. We analyze each module with several experiments and reassemble the best components to propose Assem-VC, a new state-of-the-art any-to-many non-parallel VC system. We also examine that PPG and Cotatron features are speaker-dependent, and attempt to remove speaker identity with adversarial training. Code and audio samples are available at https://github.com/mindslab-ai/assem-vc.

引用

页码：6997 / 7001

页数：5

共 24 条

[1] Ardila R., 2019, ARXIV191206670
[2] YIN, a fundamental frequency estimator for speech and music
de Cheveigné, A
Kawahara, H
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2002, 111 (04) : 1917 - 1930
[3] Dumoulin V., 2017, INT C LEARN REPR
[4] Ganin Y, 2016, J MACH LEARN RES, V17
[5] Kong Jungil, 2020, ADV NEUR IN, V33
[6] Transferring Source Style in Non-Parallel Voice Conversion
Liu, Songxiang
Cao, Yuewen
Kang, Shiyin
Hu, Na
Liu, Xunying
Su, Dan
Yu, Dong
Meng, Helen
[J]. INTERSPEECH 2020, 2020, : 4721 - 4725
[7] One-shot Voice Conversion with Global Speaker Embeddings
Lu, Hui
Wu, Zhiyong
Dai, Dongyang
Li, Runnan
Kang, Shiyin
Jia, Jia
Meng, Helen
[J]. INTERSPEECH 2019, 2019, : 669 - 673
[8] Panayotov V, 2015, INT CONF ACOUST SPEE, P5206, DOI 10.1109/ICASSP.2015.7178964
[9] Cotatron: Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel Data
Park, Seung-won
Kim, Doo-young
Joe, Myun-chul
[J]. INTERSPEECH 2020, 2020, : 4696 - 4700
[10] TTS Skins: Speaker Conversion via ASR
Polyak, Adam
Wolf, Lior
Taigman, Yaniv
[J]. INTERSPEECH 2020, 2020, : 786 - 790

← 1 2 3 →