arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.07815eess.AScs.SD
收藏

ConVoice:基于卷积网络的实时Zero-Shot语音风格传输

ConVoice: Real-Time Zero-Shot Voice Style Transfer with Convolutional Network

Higher School of Economics(高等经济大学)

Yurii Rebryk, Stanislav Beliaev

摘要:

我们提出了一个神经网络的zero-shot语音转换(VC)没有任何并行或转录数据。我们的方法使用预先训练的模型,从说话人验证任务中获得的自动语音识别(ASR)和说话人嵌入。我们的模型是完全卷积和非自回归的,除了一个小的预先训练的递归神经网络用于扬声器编码。ConVoice可以转换任何长度的语音,而不会因其卷积架构而影响质量。我们的模型具有类似的国家的最先进的模型,同时非常快的质量。

英文摘要:

We propose a neural network for zero-shot voice conversion (VC) without any parallel or transcribed data. Our approach uses pre-trained models for automatic speech recognition (ASR) and speaker embedding, obtained from a speaker verification task. Our model is fully convolutional and non-autoregressive except for a small pre-trained recurrent neural network for speaker encoding. ConVoice can convert speech of any length without compromising quality due to its convolutional architecture. Our model has comparable quality to similar state-of-the-art models while being extremely fast.

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。

↑