TorchAudio-Squim:TorchAudio中的无参考语音质量与可懂度测量
TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio
AI总结:
本文介绍了TorchAudio-Squim工具,利用深度神经网络以无参考方式估计语音的客观和主观质量指标,为语音处理研究提供便捷的评估手段。
摘要:
测量语音信号的质量和可懂度通常是语音处理系统开发中的关键步骤。为此,人们开发了各种在不同假设下测量质量和可懂度的指标。通过本文,我们介绍了使用深度神经网络估计此类已知指标的工具和一组模型。这些模型在成熟的 TorchAudio 库中提供,该库是 PyTorch 深度学习框架内的核心音频和语音处理库。我们将其称为 TorchAudio-Squim,即 TorchAudio-Speech QUality and Intelligibility Measures。更具体地说,在当前版本的 TorchAudio-squim 中,我们建立并发布了用于估计客观指标中的 PESQ、STOI 和 SI-SDR 以及主观指标中的 MOS 的模型。我们开发了一种用于客观指标估计的新方法,并使用最近开发的方法进行主观指标估计。这些模型以“无参考”方式运行,即它们不需要相应的干净语音作为语音评估的参考。鉴于现实情况中干净语音的不可得性以及主观评估过程的费力程度,此类易于使用的工具将极大地造福语音处理研究和开发。
英文摘要:
Measuring quality and intelligibility of a speech signal is usually a critical step in development of speech processing systems. To enable this, a variety of metrics to measure quality and intelligibility under different assumptions have been developed. Through this paper, we introduce tools and a set of models to estimate such known metrics using deep neural networks. These models are made available in the well-established TorchAudio library, the core audio and speech processing library within the PyTorch deep learning framework. We refer to it as TorchAudio-Squim, TorchAudio-Speech QUality and Intelligibility Measures. More specifically, in the current version of TorchAudio-squim, we establish and release models for estimating PESQ, STOI and SI-SDR among objective metrics and MOS among subjective metrics. We develop a novel approach for objective metric estimation and use a recently developed approach for subjective metric estimation. These models operate in a ``reference-less" manner, that is they do not require the corresponding clean speech as reference for speech assessment. Given the unavailability of clean speech and the effortful process of subjective evaluation in real-world situations, such easy-to-use tools would greatly benefit speech processing research and development.
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。