arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.13642eess.AS
收藏

基于学习的后验语音存在概率估计及其应用

Learning-based A Posteriori Speech Presence Probability Estimation and Applications

Shuai Tao, Jesper Rindom Jensen, Yang Xiang, Himavanth Reddy, Qingzheng Zhang, Mads Græsbøll Christensen

AI总结:

本文提出一种基于深度学习的后验语音存在概率估计方法,融合全局与局部信息,在非平稳噪声下提高估计精度,并应用于噪声PSD估计和语音增强,实验验证了其高效性能。

摘要:

后验语音存在概率(SPP)是噪声功率谱密度(PSD)估计的基本组成部分,有助于语音增强和语音识别系统。大多数现有的SPP估计器能够从背景噪声中准确估计SPP。然而,仍存在诸多挑战,包括基于统计的方法难以从非平稳噪声中准确估计SPP,以及基于深度学习的方法存在高延迟。本文提出了一种基于深度学习的改进SPP估计方法,以提高SPP估计精度,尤其是在非平稳噪声条件下。为了提升DNN的信息提取性能,将观测信号的全局信息与从观测信号中解耦的频率点的局部信息连接为混合全局-局部信息。全局信息由一个编码器提取。然后,使用一个解码器和两个全连接层从残差连接的信息中估计SPP。为了评估我们提出的SPP估计器的性能,执行了噪声PSD估计和语音增强任务。与现有的基于最小均方误差(MMSE)的噪声PSD估计方法相比,噪声PSD是基于当前帧SPP估计通过次优MMSE估计的,无需平滑。在噪声PSD估计的指导下,采用标准的语音增强框架——对数谱幅度估计器,从观测信号中提取干净语音。实验结果表明,我们提出的SPP估计器在低模型复杂度下能够实现高噪声PSD估计精度和语音增强性能。

英文摘要:

The a posteriori speech presence probability (SPP) is the fundamental component of noise power spectral density (PSD) estimation, which can contribute to speech enhancement and speech recognition systems. Most existing SPP estimators can estimate SPP accurately from the background noise. Nevertheless, numerous challenges persist, including the difficulty of accurately estimating SPP from non-stationary noise with statistics-based methods and the high latency associated with deep learning-based approaches. This paper presents an improved SPP estimation approach based on deep learning to achieve higher SPP estimation accuracy, especially in non-stationary noise conditions. To promote the information extraction performance of the DNN, the global information of the observed signal and the local information of the decoupled frequency bins from the observed signal are connected as hybrid global-local information. The global information is extracted by one encoder. Then, one decoder and two fully connected layers are used to estimate SPP from the information of residual connection. To evaluate the performance of our proposed SPP estimator, the noise PSD estimation and speech enhancement tasks are performed. In contrast to existing minimum mean-square error (MMSE)-based noise PSD estimation approaches, the noise PSD is estimated by the sub-optimal MMSE based on the current frame SPP estimate without smoothing. Directed by the noise PSD estimate, a standard speech enhancement framework, the log spectral amplitude estimator, is employed to extract clean speech from the observed signal. From the experimental results, we can confirm that our proposed SPP estimator can achieve high noise PSD estimation accuracy and speech enhancement performance while requiring low model complexity.

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。

↑