A Detection Method of Lip-smack in Spontaneous Speech
Lip-smack is one of the background events that current speech recognizers can not effectively handle. Little work has been done on the detection of lip-smack. In this paper, lip-smack characteristics in spontaneous speech are analyzed, and then a lip-smack detection method is proposed. A continuous signal is first split into silence and non-silence signal segments, and then potential lip-smack segments are extracted from the non-silence signal segments. Then Hidden Markov Models (HMMs) are trained and employed to recognize lip-smacks from potential lip-smack segments. The experimental results evaluated on three mandarin spontaneous speech corpora show that the proposed method can effectively detect lip-smacks in spontaneous speech with an average precision rate and recall rate of 80.9% and 87.4%, respectively.
Yanxiong Li Qianhua He Tao Li Weining Wang
School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510640, China
国际会议
2008 International Conference on Audio，Language and Image Processing(2008国际声音、语言、图像过程大会)
镇江
英文
292-297
2008-07-07（万方平台首次上网日期，不代表论文的发表时间）