arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.11906eess.AScs.SD
收藏

神经语音生成中的背景噪声处理

Handling Background Noise in Neural Speech Generation

Google LLC(谷歌有限责任公司);Victoria University of Wellington(惠灵顿维多利亚大学)

Tom Denton, Alejandro Luebs, Felicia S. C. Lim, Andrew Storus, Hengchin Yeh, W. Bastiaan Kleijn, Jan Skoglund

摘要:

基于神经网络的语音生成模型的最新进展为语音编码显示了巨大的潜力。然而,当输入不是干净语音时,例如,在存在背景噪声的情况下,阻止其在实际应用中的使用。在本文中,我们研究的原因和讨论的方法来克服这个问题。在训练过程中提取特征和目标干净语音时放置去噪预处理阶段被证明是性能最好的策略。

英文摘要:

Recent advances in neural-network based generative modeling of speech has shown great potential for speech coding. However, the performance of such models drops when the input is not clean speech, e.g., in the presence of background noise, preventing its use in practical applications. In this paper we examine the reason and discuss methods to overcome this issue. Placing a denoising preprocessing stage when extracting features and target clean speech during training is shown to be the best performing strategy.

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。

↑