Vowel recognition according to lip shapes by using neural network
Vowel recognition according to lip shapes by using neural network
复制标题
使用神经网络根据唇形识别元音
DOI：
10.1109/ijcnn.1998.687125
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
R. Konishi
中科院分区：
文献类型：
--
作者：
T. Shinchi;Y. Maeda;K. Sugahara;R. Konishi
尽管语音识别技术已经开发成功，但是环境的噪声会导致严重的识别错误。在这种情况下，我们期望嘴唇形状是有用的数据，作为支持数据来提高识别性能。我们提出了一种使用活动轮廓模型从输入人脸图像中提取嘴唇形状的方法。经过变换和标准化后，提取的数据被输入到神经网络以识别元音。元音识别的实验结果证实了该方法的有效性。
Although speech recognition techniques have been successfully developed, the noise of the circumstances causes serious errors in recognition. In such cases, we expect that lip shapes are useful data as supporting data to improve the performance of recognition. We propose a method to extract lip shapes from input face images by using an active contour model. After transformation and normalization the extracted data are input to a neural network to recognize vowels. Experimental results of vowel recognition are shown to confirm effectiveness of the proposed method.