Towards real-world objective speech quality and intelligibility assessment using speech-enhancement residuals and convolutional long short-term memory networks
Towards real-world objective speech quality and intelligibility assessment using speech-enhancement residuals and convolutional long short-term memory networks
复制标题
DOI：
10.1121/10.0002702
复制
发表时间：
2020-11-01
影响因子：
2.4
通讯作者：
Williamson, Donald S.
中科院分区：
文献类型：
--
作者：
Dong, Xuan;Williamson, Donald S.
语音质量感知评价（PESQ）、短时客观可懂度（STOI）和信号失真比（SDR）等客观指标常用于语音评价。这些度量是侵入性的，因为它们需要参考（干净）语音信号来完成评估。对参考信号的需求降低了这些度量的实用性，因为在真实世界的测试期间通常无法获得干净的参考信号。在本文中，提出了一个两阶段的方法，估计这些侵入性指标的客观分数在一个非侵入性的方式，这使得在现实世界的环境中进行测试。更具体地，客观分数估计被视为机器学习问题，并且提出使用语音增强残差和卷积长短期记忆（SER-CL）网络来盲估计客观分数（即，PESQ、STOI和SDR）。在模拟和真实的环境中，包含不同的组合的噪声和混响的方法进行评估。结果表明，所提出的方法是一个合理的替代评估语音，它表现良好的准确性和相关性。所提出的方法在几种环境中也优于比较方法。
Objective metrics, such as the perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and signal-to-distortion ratio (SDR), are often used for evaluating speech. These metrics are intrusive since they require a reference (clean) speech signal to complete the evaluation. The need for a reference signal reduces the practicality of these metrics, since a clean reference signal is not typically available during real-world testing. In this paper, a two-stage approach is presented that estimates the objective score of these intrusive metrics in a non-intrusive manner, which enables testing in real-world environments. More specifically, objective score estimation is treated as a machine-learning problem, and the use of speech-enhancement residuals and convolutional long short-term memory (SER-CL) networks is proposed to blindly estimate the objective scores (i.e., PESQ, STOI, and SDR) of various speech signals. The approach is evaluated in simulated and real environments that contain different combinations of noise and reverberation. The results reveal that the proposed approach is a reasonable alternative for evaluating speech, where it performs well in terms of accuracy and correlation. The proposed approach also outperforms comparison approaches in several environments.