Understanding Three Simultaneous Speeches
Understanding Three Simultaneous Speeches
复制标题
理解三个同时讲话
DOI：
--
复制
发表时间：
1997
期刊：
影响因子：
--
通讯作者：
T. Kawabata
中科院分区：
文献类型：
--
作者：
HIroshi G. Okuno;T. Nakatani;T. Kawabata
在人工智能、语音和声音理解或识别以及计算听觉场景分析研究中，同时理解三个语音被提出作为一个挑战问题。噪声环境下的自动语音识别主要采用降噪和说话人自适应等语音增强技术。然而，两段同步语音的信噪比较差，无法应用这些技术。因此，需要开发新的技术。一个备选方案是使用语音流分离作为自动语音识别系统的前端。对两个同步语音的初步理解实验表明，基于语音流分离的挑战问题是可行的。针对所提出的挑战问题，给出了详细的研究方案和基准声音。
Understanding three simultaneous speeches is proposed as a challenge problem to foster artificial intelligence, speech and sound understanding or recognition, and computational auditory scene analysis research. Automatic speech recognition under noisy environments is attacked by speech enhancement techniques such as noise reduction and speaker adaptation. However, the signal-to-noise ratio of speech in two simultaneous speeches is too poor to apply these techniques. Therefore, novel techniques need to be developed. One candidate is to use speech stream segregation as a front-end of automatic speech recognition systems. Preliminary experiments on understanding two simultaneous speeches show that the proposed challenge problem will be feasible with speech stream segregation. The detailed plan of the research on and benchmark sounds for the proposed challenge problem is also presented.