TY - GEN
T1 - Many-To-Many Voice Conversion Using Conditional Cycle-Consistent Adversarial Networks
AU - Lee, Shindong
AU - Ko, Bonggu
AU - Lee, Keonnyeong
AU - Yoo, In Chul
AU - Yook, Dongsuk
N1 - Funding Information:
This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and Future Planning (NRF-2017R1E1A1A01078157). Also, it was partly supported by the MSIT (Ministry of Science and ICT) under the ITRC (Information Technology Research Center) support program (IITP-2018-0-01405) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation), and IITP grant funded by the Korean government (MSIT) (No. 2018-0-00269).
Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - Voice conversion (VC) refers to transforming the speaker characteristics of an utterance without altering its linguistic contents. Many works on voice conversion require to have parallel training data that is highly expensive to acquire. Recently, the cycle-consistent adversarial network (CycleGAN), which does not require parallel training data, has been applied to voice conversion, showing the state-of-the-art performance. The CycleGAN based voice conversion, however, can be used only for a pair of speakers, i.e., one-to-one voice conversion between two speakers. In this paper, we extend the CycleGAN by conditioning the network on speakers. As a result, the proposed method can perform many-to-many voice conversion among multiple speakers using a single generative adversarial network (GAN). Compared to building multiple CycleGANs for each pair of speakers, the proposed method reduces the computational and spatial cost significantly without compromising the sound quality of the converted voice. Experimental results using the VCC2018 corpus confirm the efficiency of the proposed method.
AB - Voice conversion (VC) refers to transforming the speaker characteristics of an utterance without altering its linguistic contents. Many works on voice conversion require to have parallel training data that is highly expensive to acquire. Recently, the cycle-consistent adversarial network (CycleGAN), which does not require parallel training data, has been applied to voice conversion, showing the state-of-the-art performance. The CycleGAN based voice conversion, however, can be used only for a pair of speakers, i.e., one-to-one voice conversion between two speakers. In this paper, we extend the CycleGAN by conditioning the network on speakers. As a result, the proposed method can perform many-to-many voice conversion among multiple speakers using a single generative adversarial network (GAN). Compared to building multiple CycleGANs for each pair of speakers, the proposed method reduces the computational and spatial cost significantly without compromising the sound quality of the converted voice. Experimental results using the VCC2018 corpus confirm the efficiency of the proposed method.
KW - Conditional CycleGAN (CC-GAN)
KW - Cycle-consistent Adversarial Network (CycleGAN)
KW - Generative Adversarial Networks (GAN)
KW - Voice Conversion
UR - http://www.scopus.com/inward/record.url?scp=85089220417&partnerID=8YFLogxK
U2 - 10.1109/ICASSP40776.2020.9053726
DO - 10.1109/ICASSP40776.2020.9053726
M3 - Conference contribution
AN - SCOPUS:85089220417
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 6279
EP - 6283
BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Y2 - 4 May 2020 through 8 May 2020
ER -