Back to Search
Start Over
Unsupervised Representation Disentanglement Using Cross Domain Features and Adversarial Learning in Variational Autoencoder Based Voice Conversion
- Source :
- IEEE Transactions on Emerging Topics in Computational Intelligence. 4:468-479
- Publication Year :
- 2020
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2020.
-
Abstract
- An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this principle. In our prior work, we proposed a cross-domain VAE-VC (CDVAE-VC) framework, which utilized acoustic features of different properties, to improve the performance of VAE-VC. We believed that the success came from more disentangled latent representations. In this paper, we extend the CDVAE-VC framework by incorporating the concept of adversarial learning, in order to further increase the degree of disentanglement, thereby improving the quality and similarity of converted speech. More specifically, we first investigate the effectiveness of incorporating the generative adversarial networks (GANs) with CDVAE-VC. Then, we consider the concept of domain adversarial training and add an explicit constraint to the latent representation, realized by a speaker classifier, to explicitly eliminate the speaker information that resides in the latent code. Experimental results confirm that the degree of disentanglement of the learned latent representation can be enhanced by both GANs and the speaker classifier. Meanwhile, subjective evaluation results in terms of quality and similarity scores demonstrate the effectiveness of our proposed methods.<br />Accepted to IEEE Transactions on Emerging Topics in Computational Intelligence
- Subjects :
- FOS: Computer and information sciences
Sound (cs.SD)
Computer Science - Machine Learning
Computer Science - Computation and Language
Control and Optimization
Computer science
Speech recognition
Speech processing
Autoencoder
Computer Science - Sound
Machine Learning (cs.LG)
Computer Science Applications
Domain (software engineering)
Constraint (information theory)
Computational Mathematics
Audio and Speech Processing (eess.AS)
Artificial Intelligence
Similarity (psychology)
Classifier (linguistics)
FOS: Electrical engineering, electronic engineering, information engineering
Code (cryptography)
Representation (mathematics)
Computation and Language (cs.CL)
Electrical Engineering and Systems Science - Audio and Speech Processing
Subjects
Details
- ISSN :
- 2471285X
- Volume :
- 4
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Emerging Topics in Computational Intelligence
- Accession number :
- edsair.doi.dedup.....7b7ad09f961eeffff8b148c081839d18