VISinger2+: End-to-End Singing Voice Synthesis Augmented by Self-Supervised Learning Representation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917868099076096 |
|---|---|
| author | Yu, Yifeng Shi, Jiatong Wu, Yuning Tang, Yuxun Watanabe, Shinji |
| author_facet | Yu, Yifeng Shi, Jiatong Wu, Yuning Tang, Yuxun Watanabe, Shinji |
| contents | Singing Voice Synthesis (SVS) has witnessed significant advancements with the advent of deep learning techniques. However, a significant challenge in SVS is the scarcity of labeled singing voice data, which limits the effectiveness of supervised learning methods. In response to this challenge, this paper introduces a novel approach to enhance the quality of SVS by leveraging unlabeled data from pre-trained self-supervised learning models. Building upon the existing VISinger2 framework, this study integrates additional spectral feature information into the system to enhance its performance. The integration aims to harness the rich acoustic features from the pre-trained models, thereby enriching the synthesis and yielding a more natural and expressive singing voice. Experimental results in various corpora demonstrate the efficacy of this approach in improving the overall quality of synthesized singing voices in both objective and subjective metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08761 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VISinger2+: End-to-End Singing Voice Synthesis Augmented by Self-Supervised Learning Representation Yu, Yifeng Shi, Jiatong Wu, Yuning Tang, Yuxun Watanabe, Shinji Sound Audio and Speech Processing Singing Voice Synthesis (SVS) has witnessed significant advancements with the advent of deep learning techniques. However, a significant challenge in SVS is the scarcity of labeled singing voice data, which limits the effectiveness of supervised learning methods. In response to this challenge, this paper introduces a novel approach to enhance the quality of SVS by leveraging unlabeled data from pre-trained self-supervised learning models. Building upon the existing VISinger2 framework, this study integrates additional spectral feature information into the system to enhance its performance. The integration aims to harness the rich acoustic features from the pre-trained models, thereby enriching the synthesis and yielding a more natural and expressive singing voice. Experimental results in various corpora demonstrate the efficacy of this approach in improving the overall quality of synthesized singing voices in both objective and subjective metrics. |
| title | VISinger2+: End-to-End Singing Voice Synthesis Augmented by Self-Supervised Learning Representation |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.08761 |