Again-VC: A One-Shot Voice Conversion Using Activation Guidance and Adaptive Instance Normalization
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5954-5958
Abstract
Recently, voice conversion (VC) has been widely studied. Many VC systems use disentangle-based learning techniques to separate the speaker and the linguistic content information from a speech signal. Subsequently, they convert the voice by changing the speaker information to that of the target speaker. To prevent the speaker information from leaking into the content embeddings, previous works either reduce the dimension or quantize the content embedding as a strong information bottleneck. These mechanisms somehow hurt the synthesis quality. In this work, we propose AGAIN-VC, an innovative VC system using Activation Guidance and Adaptive Instance Normalization. AGAIN-VC is an auto-encoder-based model, comprising of a single encoder and a decoder. With a proper activation as an information bottleneck on content embeddings, the trade-off between the synthesis quality and the speaker similarity of the converted speech is improved drastically. This one-shot VC system obtains the best performance regardless of the subjective or objective evaluations.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational AutoencoderIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- Cyclegan-VC2: Improved Cyclegan-based Non-parallel Voice Conversion2019
- StarGAN-VC: non-parallel many-to-many Voice Conversion Using Star Generative Adversarial Networks2018
- Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders2018
- Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations2018
- CycleGAN-VC: Non-parallel Voice Conversion Using Cycle-Consistent Adversarial Networks2018
- Generalized End-to-End Loss for Speaker Verification2018
- Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization2017
- Voice Conversion from Unaligned Corpora Using Variational Autoencoding Wasserstein Generative Adversarial Networks2017
- Voice conversion from non-parallel corpora using variational auto-encoder2016