기본 설정은 nvidia drivers는 설치된 상태로 간주함.
Docker기반이긴 하지만 conda 환경이면 무리없이 적용될 것.
(참고)geometric 배포자들은 local환경보다 가상환경을 추천하고 있음.
귀찮은 사람들은 그냥 python=3.7.16 , cuda 11.7으로 세팅해놓고 아래 배포해놓은 requirements.txt 실행 ㄱ
docker hub에 공개되어 있는 cuda11.7, ubuntu 20.04인 이미지를 다운받음
출처
Sadekova, Tasnima, et al. “A Unified System for Voice Cloning and Voice Conversion through Diffusion Probabilistic Modeling}}.” Proc. Interspeech 2022 (2022): 3003-3007.
Lian, Jiachen, Chunlei Zhang, and Dong Yu. “Robust disentangled variational speech representation learning for zero-shot voice conversion.” ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022.
Copyright of figures and other materials in the paper belongs to original authors.
출처
Nguyen, Bac, and Fabien Cardinaux. “Nvc-net: End-to-end adversarial voice conversion.” ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022.APA
출처
Kim, Changhwan, et al. “FluentTTS: Text-dependent Fine-grained Style Control for Multi-style TTS.” Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2022. 2022.
출처
Khorram, Soheil, et al. “Contrastive Siamese Network for Semi-Supervised Speech Recognition.” ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022.
Copyright of figures and other materials in the paper belongs to original authors.