Using Acoustic Parameters for Intelligibility Prediction of Reverberant Speech
Using Acoustic Parameters for Intelligibility Prediction of Reverberant Speech
复制标题
使用声学参数进行混响语音的清晰度预测
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Daniel Fogerty
中科院分区：
文献类型：
--
作者：
Ahmed Alghamdi;W. Chan;Daniel Fogerty
这项工作解决了预测混响语音的主观可懂度的问题。使用新的主观听音测试数据，我们评估了三个客观的可懂度措施，可以从房间脉冲响应计算的性能。这些措施被发现与混响语音的单词和音素识别率相关。特别是，所检查的措施之一更容易涉及空间维度，因此可能更方便的环境跟踪声学接口应用。
This work addresses the problem of predicting the subjective intelligibility of reverberant speech. Using new subjective listening test data, we evaluate the performance of three objective intelligibility measures that can be computed from the room impulse response. The measures are found to correlate well with the word and phoneme recognition rates of reverberant speech. In particular, one of the examined measures more readily relates to spatial dimensions and hence may be more convenient for environment-tracking acoustic interface applications.