Mel-S3R: Combining Mel-spectrogram and self-supervised speech representation with VQ-VAE for any-to-any voice conversion

Yang, Jichen; Zhou, Yi; Huang, Hao

doi:10.1016/j.specom.2023.05.004

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Book1

Preprint1

Article1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Improving Voice Style Conversion via Self-attention VAE with Feature Disentanglement

Yuan,

Li,

Zhao

et al. 2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Improving Voice Style Conversion via Self-attention VAE with Feature Disentanglement

Yuan,

Li,

Zhao

et al. 2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Coal Gangue Recognition in the Strong Background Noise Using Two-Level Auditory Feature Fusion with Attention Mechanism

Yang,

Wang,

Yang

et al. 2024

Preprint

View full text Add to dashboard Cite

Reimagining speech: a scoping review of deep learning-based methods for non-parallel voice conversion

Bargum,

Serafin,

Erkut

2024

Front. Signal Process.

View full text Add to dashboard Cite

Research on deep learning-powered voice conversion (VC) in speech-to-speech scenarios are gaining increasing popularity. Although many of the works in the field of voice conversion share a common global pipeline, there is considerable diversity in the underlying structures, methods, and neural sub-blocks used across research efforts. Thus, obtaining a comprehensive understanding of the reasons behind the choice of the different methods included when training voice conversion models can be challenging, and the actual hurdles in the proposed solutions are often unclear. To shed light on these aspects, this paper presents a scoping review that explores the use of deep learning in speech analysis, synthesis, and disentangled speech representation learning within modern voice conversion systems. We screened 628 publications from more than 38 venues between 2017 and 2023, followed by an in-depth review of a final database of 130 eligible studies. Based on the review, we summarise the most frequently used approaches to voice conversion based on deep learning and highlight common pitfalls. We condense the knowledge gathered to identify main challenges, supply solutions grounded in the analysis and provide recommendations for future research directions.

show abstract

Mel-S3R: Combining Mel-spectrogram and self-supervised speech representation with VQ-VAE for any-to-any voice conversion

Cited by 3 publications

References 43 publications

Improving Voice Style Conversion via Self-attention VAE with Feature Disentanglement

Improving Voice Style Conversion via Self-attention VAE with Feature Disentanglement

Coal Gangue Recognition in the Strong Background Noise Using Two-Level Auditory Feature Fusion with Attention Mechanism

Reimagining speech: a scoping review of deep learning-based methods for non-parallel voice conversion

Contact Info

Product

Resources

About