arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.02585cs.SDcs.LGeess.AS
收藏

InQSS:一种使用多任务学习网络的语音清晰度和质量评估模型

InQSS: a speech intelligibility and quality assessment model using a multi-task learning network

Research Center for Information Technology Innovation, Academia Sinica(中央研究院资讯科技创新研究中心)

Yu-Wen Chen, Yu Tsao

摘要:

语音清晰度和质量评估模型是研究人员评估和改进语音处理模型的重要工具。然而,由于现有数据的限制,只有少数研究调查了多任务模型的可懂度和质量评估。在这项研究中,我们发布了TMHINT-QI,这是第一个记录了干净,嘈杂和增强话语的质量和可懂度分数的中文语音数据集。然后,我们提出了InQSS,一个非侵入式的多任务学习框架的可理解性和质量评估。我们在从头开始训练和预训练模型上评估了InQSS。实验结果证实了InQSS框架的有效性。此外,所得到的模型不仅可以预测可懂度分数,而且可以预测语音信号的质量分数。

英文摘要:

Speech intelligibility and quality assessment models are essential tools for researchers to evaluate and improve speech processing models. However, only a few studies have investigated multi-task models for intelligibility and quality assessment due to the limitations of available data. In this study, we released TMHINT-QI, the first Chinese speech dataset that records the quality and intelligibility scores of clean, noisy, and enhanced utterances. Then, we propose InQSS, a non-intrusive multi-task learning framework for intelligibility and quality assessment. We evaluated the InQSS on both the training-from-scratch and the pretrained models. The experimental results confirm the effectiveness of the InQSS framework. In addition, the resulting model can predict not only the intelligibility scores but also the quality scores of a speech signal.

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。

↑