基于强制对齐的汉语重复性口吃检测方法研究  

A forced alignment approach to detect Chinese repetitive stuttering

作　　者：张俊博[1] 严芊 高兴龙[1] 潘复平[1] 冯勇强[1] 邢力力 林春兰 潘接林[1] 

机构地区：[1]中国科学院声学研究所语言声学与内容理解重点实验室,北京100190 [2]林教授言语训练中心,北京102600

出　　处：《声学学报》2013年第3期397-404,共8页Acta Acustica

基　　金：国家自然科学基金(10925419;90920302;61072124;11074275;11161140319;91120001);中国科学院战略性先导科技专项(面向感知中国的新一代信息技术研究;XDA06030100;XDA06030500);国家863计划(2012AA012503)经费资助项目

摘　　要：研究了基于强制对齐的针对汉语的口吃自动检测算法。针对汉语重复性口吃的特点,设计了改进的方案。首先为检测汉语口吃的多音节重复现象,设计了多跨度回环的强制对齐解码网络。然后为降低由于解码网络的复杂化带来的误差,用回溯搜索方法在网络中加入了支路惩罚因子以调节解码趋向。最后为进一步提高检测结果的可靠性,计算置信度,对重复性口吃现象进行了二次判决。试验结果表明,与现有算法相比,采用的改进算法能使重复性口吃检测的错误率相对降低18%左右,有效地改善了重复性口吃检测系统的性能。A forced alignment based Mgorithm to detect chinese repetitive stuttering is studied. According to the features of repetitions in Chinese stuttered speech, improvement solutions are provided based on the previous research findings. First, a multi-span looping forced alignment decoding network is designed to detect multi-syllable repetitions in Chinese stuttered speech. Second, branch penalty is added in the network to adjust decoding trend using recursive search in order to reduce the error from the complexity of the decoding network. Finally, we rejudge the detected stutters by calculating confidence to improve the reliability of the detection result. The experimental results show that compared to previous algorithm, the proposed algorithm can improve system performance significantly, about 18% reduction of average detection error rate relatively.

关 键 词：自动检测算法 重复性 汉语 对齐 解码网络 惩罚因子 搜索方法 检测结果 

分 类 号：TN912.3[电子电信—通信与信息系统]