تقرير
TokSing: Singing Voice Synthesis based on Discrete Tokens
| العنوان: | TokSing: Singing Voice Synthesis based on Discrete Tokens |
|---|---|
| المؤلفون: | Wu, Yuning, zhang, Chunlei, Shi, Jiatong, Tang, Yuxun, Yang, Shan, Jin, Qin |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing |
| الوصف: | Recent advancements in speech synthesis witness significant benefits by leveraging discrete tokens extracted from self-supervised learning (SSL) models. Discrete tokens offer higher storage efficiency and greater operability in intermediate representations compared to traditional continuous Mel spectrograms. However, when it comes to singing voice synthesis(SVS), achieving higher levels of melody expression poses a great challenge for utilizing discrete tokens. In this paper, we introduce TokSing, a discrete-based SVS system equipped with a token formulator that offers flexible token blendings. We observe a melody degradation during discretization, prompting us to integrate a melody signal with the discrete token and incorporate a specially-designed melody enhancement strategy in the musical encoder. Extensive experiments demonstrate that our TokSing achieves better performance against the Mel spectrogram baselines while offering advantages in intermediate representation space cost and convergence speed. Comment: Accepted by Interspeech 2024 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2406.08416 |
| رقم الأكسشن: | edsarx.2406.08416 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |