Learning Disentangled Speech Representations with Contrastive Learning and Time-Invariant Retrieval

The framework of CTVC

Abstract

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio has the potential ability to well represent content. Besides, the speaker-style modeling with pre-trained models making the process more complex. To tackle these issues, we introduce a new method named “CTVC” which utilizes disentangled speech representations with contrastive learning and time-invariant retrieval. Specifically, a similarity-based compression module is used to facilitate a more intimate connection between the frame-level hidden features and linguistic information at phoneme-level. Additionally, a time-invariant retrieval is proposed for timbre extraction based on multiple segmentations and mutual information. Experimental results demonstrate that “CTVC” outperforms previous studies and improves the sound quality and similarity of converted results.

Type
Publication
In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Yimin Deng
Yimin Deng
University of Science and Technology of China
Huaizhen Tang
Huaizhen Tang
University of Science and Technology of China
Ning Cheng
Ning Cheng
Director