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 2008.11920eess.AS
收藏

Dynamic Noise Embedding:用于语音增强的噪声感知训练和自适应

Dynamic Noise Embedding: Noise Aware Training and Adaptation for Speech Enhancement

Joohyung Lee, Youngmoon Jung, Myunghun Jung, Hoirin Kim

摘要:

准确估计噪声信息对于语音应用中的噪声感知训练至关重要,包括语音增强(SE),这也是本文研究的重点。为了估计只有噪声的帧,我们采用语音活动检测(VAD)检测非语音帧通过应用最佳阈值的语音后验。这里,非语音帧可以被认为是噪声信号中的仅噪声帧。这些估计的帧被用来提取噪声嵌入,称为动态噪声嵌入(DNE),这是有用的SE模块捕获的背景噪声的特性。DNE由一个简单的神经网络提取,SE模块与DNE可以联合训练,以适应环境。在TIMIT数据集上进行了单通道去噪任务的实验,并将U-Net用作骨干SE模块。实验结果表明,DNE在SE模块中起着重要的作用,通过提高质量和可懂度的损坏的信号,即使噪声是非平稳的,在训练中看不见的。此外,我们证明了DNE可以灵活地应用于其他基于神经网络的SE模块。

英文摘要:

Estimating noise information exactly is crucial for noise aware training in speech applications including speech enhancement (SE) which is our focus in this paper. To estimate noise-only frames, we employ voice activity detection (VAD) to detect non-speech frames by applying optimal threshold on speech posterior. Here, the non-speech frames can be regarded as noise-only frames in noisy signal. These estimated frames are used to extract noise embedding, named dynamic noise embedding (DNE), which is useful for an SE module to capture the characteristic of background noise. The DNE is extracted by a simple neural network, and the SE module with the DNE can be jointly trained to be adaptive to the environment. Experiments are conducted on TIMIT dataset for single-channel denoising task and U-Net is used as a backbone SE module. Experimental results show that the DNE plays an important role in the SE module by increasing the quality and the intelligibility of corrupted signal even if the noise is non-stationary and unseen in training. In addition, we demonstrate that the DNE can be flexibly applied to other neural network-based SE modules.

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。

↑