arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.08833eess.AS
收藏

使用UA-Speech和TORGO数据库验证构音障碍语音自动分类方法

On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches

Guilherme Schu, Parvaneh Janbakhshi, Ina Kodrasi

摘要:

虽然UA-语音和TORGO数据库的控制和构音障碍的语音是宝贵的资源提供给研究界的目标是开发强大的自动语音识别系统,他们也被用来验证相当数量的自动构音障碍语音分类方法。这种方法通常依赖于基本假设,即来自控制和构音障碍扬声器的录音是使用相同的录音设置在相同的无噪声环境中收集的。在本文中,我们表明,这一假设是违反了UA语音和TORGO数据库。使用语音活动检测提取语音和非语音段,我们表明,大多数国家的最先进的构音障碍分类方法实现相同或更好的性能时,使用这些数据库的非语音段比使用语音段。这些结果表明,在UA-语音和TORGO数据库上训练和验证的这种方法可能是记录环境或设置的学习特征,而不是构音障碍的语音特征。我们希望这些结果能提高研究界在开发和评估构音障碍自动分类方法时对录音质量重要性的认识。

英文摘要:

Although the UA-Speech and TORGO databases of control and dysarthric speech are invaluable resources made available to the research community with the objective of developing robust automatic speech recognition systems, they have also been used to validate a considerable number of automatic dysarthric speech classification approaches. Such approaches typically rely on the underlying assumption that recordings from control and dysarthric speakers are collected in the same noiseless environment using the same recording setup. In this paper, we show that this assumption is violated for the UA-Speech and TORGO databases. Using voice activity detection to extract speech and non-speech segments, we show that the majority of state-of-the-art dysarthria classification approaches achieve the same or a considerably better performance when using the non-speech segments of these databases than when using the speech segments. These results demonstrate that such approaches trained and validated on the UA-Speech and TORGO databases are potentially learning characteristics of the recording environment or setup rather than dysarthric speech characteristics. We hope that these results raise awareness in the research community about the importance of the quality of recordings when developing and evaluating automatic dysarthria classification approaches.

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。

↑