Speech Recognition by Image Processing of Lip Movements
Speech Recognition by Image Processing of Lip Movements
复制标题
通过嘴唇运动图像处理进行语音识别
DOI：
10.9746/sicetr1965.22.191
复制
发表时间：
1986
期刊：
影响因子：
--
通讯作者：
K. Kurosu
中科院分区：
文献类型：
--
作者：
K. Matsuoka;T. Furuya;K. Kurosu
唇读阅读是一种常规方法，可以使聋人通过视觉信息理解他人的言语。然而，掌握这项技术需要很大的努力和很长的时间，而且它的教学教育体系还没有建立起来。本文描述了一种利用图像处理和模式识别技术实现唇阅读的尝试，旨在阐明唇阅读的可能性和局限性。虽然我们的最终目标是实现语音理解，但本文只涉及日语元音和单词的识别作为第一步。用电视摄像机拍摄了嘴唇的正面或侧面图像，提取了嘴唇形状的一些特征值。用最大似然法对5个元音进行了判别，判别正确率在80%以上。此外，还进行了基于元音判别的单词识别。实验结果表明，受试者对少量单词具有显著的唇读能力。最后，结合聋人的实际唇阅读，讨论了几个问题。
Lip reading is a regular method that enables the deaf to understand other people's speech by visual information. The acquisition of the technique, however, requires great effort and long time, and the educational system for its teaching is not established yet. This paper describes an attempt to realize lip reading, using techniques of image processing and pattern recognition, in which we aim at clarifying possibilities and limitations inherently existing in lip reading. Although our final goal is the realization of speech understanding, this paper only deals with recognition of vowels and words of the Japanese language as the first step. The front or side view of the mouth is taken with a TV camera, and some feature values of the lip shape were extracted. Discrimination of five vowels were performed by the maximum-likelihood method and the vowels were correctly discriminated by more than about 80% Moreover, word recognition based upon the vowel discrimination was performed. The result showed a remarkable capability of lip readig for a small number of words. Finally, several problems are discussed in relation to the actual lip reading of the deaf.