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 2102.08706eess.AScs.LGcs.SD
收藏

基于噪声感知编码器的变分自编码语音增强

Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder

Huajian Fang, Guillaume Carbajal, Stefan Wermter, Timo Gerkmann

摘要:

最近,一种生成式变分自编码器(VAE)已被提出用于语音增强以模拟语音统计。然而,这种方法在训练阶段仅使用干净的语音,使得估计对噪声的存在特别敏感,特别是在低信噪比(SNR)下。为了增加VAE的鲁棒性,我们建议在训练阶段使用噪声感知编码器训练噪声干净的语音对,包括噪声信息。我们使用两个不同的噪声数据集对不同噪声环境和声学条件的真实记录进行评估。我们表明,我们提出的噪声感知VAE优于标准VAE的整体失真,而不增加模型参数的数量。与此同时,我们证明了我们的模型能够比监督前馈深度神经网络(DNN)更好地推广到不可见的噪声条件。此外,我们证明了模型性能的鲁棒性,以减少噪声干净的语音训练数据的大小。

英文摘要:

Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to noise presence, especially in low signal-to-noise ratios (SNRs). To increase the robustness of the VAE, we propose to include noise information in the training phase by using a noise-aware encoder trained on noisy-clean speech pairs. We evaluate our approach on real recordings of different noisy environments and acoustic conditions using two different noise datasets. We show that our proposed noise-aware VAE outperforms the standard VAE in terms of overall distortion without increasing the number of model parameters. At the same time, we demonstrate that our model is capable of generalizing to unseen noise conditions better than a supervised feedforward deep neural network (DNN). Furthermore, we demonstrate the robustness of the model performance to a reduction of the noisy-clean speech training data size.

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。

↑