arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.05236cs.SDcs.LGeess.AS
收藏

GAN声码器:多分辨率鉴别器就是您所需要的

GAN Vocoder: Multi-Resolution Discriminator Is All You Need

MoneyBrain Inc.(MoneyBrain公司)

Jaeseong You, Dalhyun Kim, Gyuhyeon Nam, Geumbyeol Hwang, Gyeongsu Chae

摘要:

几款最新的基于GAN的声码器取得了显着的成就,在定性和定量测量方面都优于自回归和基于流的竞争对手,同时合成速度也快了几个数量级。在这项工作中,我们假设他们成功的共同因素是多分辨率的判别框架,而不是在架构,损失函数,或训练策略的微小细节。我们实验测试的假设,通过评估六个不同的发电机配对一个共享的多分辨率判别框架。对于所有的评价措施,相对于文本到语音合成和所有的感知指标,他们的表现是无法区分彼此,这支持了我们的假设。

英文摘要:

Several of the latest GAN-based vocoders show remarkable achievements, outperforming autoregressive and flow-based competitors in both qualitative and quantitative measures while synthesizing orders of magnitude faster. In this work, we hypothesize that the common factor underlying their success is the multi-resolution discriminating framework, not the minute details in architecture, loss function, or training strategy. We experimentally test the hypothesis by evaluating six different generators paired with one shared multi-resolution discriminating framework. For all evaluative measures with respect to text-to-speech syntheses and for all perceptual metrics, their performances are not distinguishable from one another, which supports our hypothesis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑