采用过零刺激方案提高电子耳蜗声调识别

计算机工程与应用 ›› 2014, Vol. 50 ›› Issue (19): 232-236.

采用过零刺激方案提高电子耳蜗声调识别

倪赛华1，孙文业1，孙宝印1，周强1，王振明2，顾济华1，陶智1

1.苏州大学物理科学与技术学院，江苏苏州 215006
2.苏州大学捷美生物医学工程仪器联合重点实验室，江苏苏州 215006

出版日期:2014-10-01 发布日期:2014-09-29

Use zero-crossing stimulating strategy to enhance Mandarin tone recognition

NI Saihua1, SUN Wenye1, SUN Baoyin1, ZHOU Qiang1, WANG Zhenming2, GU Jihua1，TAO Zhi1

1.School of Physical Science and Technology, Soochow University, Suzhou, Jiangsu 215006, China
2.Jiemei, United Key Laboratory of Biomedical Engineering Instruments, Soochow University, Suzhou, Jiangsu 215006, China

Online:2014-10-01 Published:2014-09-29

摘要/Abstract

摘要： 针对目前噪声环境下电子耳蜗汉语声调和语句识别率急剧下降问题，提出了一种基于时间精细结构过零刺激方案（FSZC）。利用语音信号时间精细结构的过零点时刻产生高速脉冲刺激序列，从而不仅将时间精细结构编码到电子耳蜗语音算法中，同时采用过零点时刻非均匀的采样脉冲刺激序列，确保了语音的空间编码和时间编码。声学模拟实验表明，相比于连续交替采样策略（CIS）和过零点时刻刺激策略（ZCT），FSZC方案在汉语声调和语句识别率上都有较大程度的提高，而且在噪声环境下对于声调和语句识别具有相对较强的抗噪性。

关键词: 时间精细结构, 过零点, 汉语声调, 电子耳蜗

Abstract: The performance of Mandarin tone and sentence recognition in cochlear implant falls sharply in noise environment. In order to solve the problem, this paper proposes a coding strategy based on the Zero-Crossing time of the temporal Fine Structure（FSZC） of the speech. The high-speed pulse stimulation sequences are generated at the zero-crossing time of the fine structure, thus the coding strategy not only includes the fine structure but also uses the non-uniform pulses which ensures the spatial and time encoding of the speech. Acoustic simulation results show that compared with Continuous Interleaved Sampling（CIS） strategy and the Zero-Crossing Time（ZCT） stimulating strategy, the Mandarin tone and sentence recognition rate have improved to a greater extent with the FSZC strategy, and the FSZC strategy has a stronger anti-noise performance.

Key words: temporal fine structure, zero-crossing, Mandarin tone, Cochlear Implant（CI）

倪赛华1，孙文业1，孙宝印1，周强1，王振明2，顾济华1，陶智1. 采用过零刺激方案提高电子耳蜗声调识别[J]. 计算机工程与应用, 2014, 50(19): 232-236.

NI Saihua1, SUN Wenye1, SUN Baoyin1, ZHOU Qiang1, WANG Zhenming2, GU Jihua1，TAO Zhi1. Use zero-crossing stimulating strategy to enhance Mandarin tone recognition[J]. Computer Engineering and Applications, 2014, 50(19): 232-236.

[1]	孙文业，陶智，孙宝印，倪赛华，王振明，顾济华. 采用听觉外周模型改进电子耳蜗CIS方案[J]. 计算机工程与应用, 2014, 50(4): 215-218.
[2]	李冰，夏秀渝，申庆超，周宁. 基于过零点双耳时间差的运动声源定位[J]. 计算机工程与应用, 2012, 48(9): 127-130.
[3]	黄雅婷,顾济华,陶智,赵鹤鸣,吴迪. 一种Bark子波变换的电子耳蜗语音增强算法[J]. 计算机工程与应用, 2008, 44(5): 215-217.
[4]	施晓敏¹,顾济华¹,陶智¹,赵鹤鸣²,张晓俊¹. 基于听觉感知的电子耳蜗共振峰提取方案[J]. 计算机工程与应用, 2007, 43(29): 232-234.