VITS2来袭~

最新推荐文章于 2025-09-19 17:20:39 发布

原创最新推荐文章于 2025-09-19 17:20:39 发布 · 1k 阅读

CC 4.0 BY-SA版权

文章标签：

192 篇文章

订阅专栏

本文介绍了一种名为VITS2的改进方法，通过对抗学习和使用Transformer块进行speaker-conditioned文本编码，解决单阶段文本转语音的不连贯、低效等问题，提升了音频质量和处理多说话人特性的能力。

论文：VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

演示：https://vits-2.github.io/demo/

论文：https://arxiv.org/abs/2307.16430

目前仍然存在的问题:

intermittent unnaturalness
low efficiency of the duration predictor
complex input format to alleviate the limitations of alignment and duration modeling (use of blank token)
insufficient speaker similarity in the multi-speaker model
slow training, and strong dependence on the phoneme conversion.

提出的方法：

a stochastic duration predictor trained through adversarial learning
normalizing flows improved by utilizing the transformer block
a speaker-conditioned text encoder to model multiple speakers’ characteristics better.