基于低频带非均匀采样策略提高电子耳蜗汉语识别鲁棒性  

Low Frequency-based Non-uniform Sampling Strategy to Improve Chinese Recognition in Cochlear Implant

作　　者：倪赛华 孙文业 孙宝印[1] 周强[1] 王振明[2] 顾济华[1] 陶智[1] 

机构地区：[1]苏州大学物理科学与技术学院,苏州215006 [2]苏州大学捷关生物医学工程实验室,苏州215006

出　　处：《生物医学工程学杂志》2014年第3期520-526,共7页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(61271359);苏州大学捷美生物医学工程仪器联合重点实验室资助项目

摘　　要：提出一种基于低频带非均匀采样的电子耳蜗编码策略,即低频带精细结构(LFFS)过零刺激方案(简称LFFS方案),以提高电子耳蜗汉语声调和语音识别鲁棒性。根据频带选择法则,在人耳基频感知范围内,采用精细结构过零刺激脉冲序列。声学模拟结果表明:在安静环境下,LFFS方案和连续交替采样(CIS)方案语音识别率差别不大;在噪声环境下,LFFS方案在汉语声调、词汇和句子方面要明显优于CIS方案,同时采用改进指数分布模型得到较好的汉语识别因素分布图。LFFS方案包含了更多的汉语声调信息,所以能有效地提高电子耳蜗植入患者汉语识别鲁棒性。To enhance speech recognition, as well as Mandarin tone recognition in noice, we proposed a speech coding strategy called zero-crossing of fine structure in low frequency （LFFS） for cochlear implant based on low frequency non-uniform sampling （LFFS for short）. In the range of frequency perceived boundary of human ear, we used zero crossing time of the fine structure to generate the stimulus pulse sequences based on the frequency selection rule. A- coustic simulation results showed that although on quiet background the performance of LFFS was similar to continu- ous interleaved sampling （CIS）, on the noise background the performance of LFFS in Chinese tones, words and sen- tences were significantly better than CIS. In addition to this, we also got better Mandarin recognition factors distri- bution by using the improved index distribution model. LFFS contains more tonal information which was able to ef- fectively improve Mandarin recognition of the cochlear implant.

关 键 词：精细结构 过零点 低频带 汉语识别 电子耳蜗 

分 类 号：R318.18[医药卫生—生物医学工程]