智能辅听系统对改善人工耳蜗植入者听声效果的研究

The Effects of the Intelligent Hearing-assistive System on Hearing Benefits to Cochlear Implant Recipients

项丽阳;李娟娟;韩彦;王金剑;杨典;杨婷君;银力;黄穗

1:浙江诺尔康神经电子科技股份有限公司

2:浙江省神经电子与脑机接口技术重点实验室

3:深圳市龙岗区耳鼻咽喉医院

摘要
目的 了解诺尔康人工耳蜗处理器中搭载的智能辅听系统自动识别声音场景并进行智能化的声音处理策略配置及其在改善人工耳蜗植入者主客观听声效果方面的作用。方法 为评估诺尔康智能辅听系统中声音场景识别模块的性能:(1)为评估场景识别模块的性能,在隔声室环境中播放预设的语音、噪声、带噪语音、纯音乐主带人声音乐5种测试音频(每类测试音频包括6~9个5 min时长的测试文件),统计各类音频的识别准确率和场景切换次数;(2)为评估该系统中语音增强模块中的ABeam技术的降噪效果,招募13例诺尔康人工耳蜗植入者,分别在ABeam “ON”和“OFF”程序下,在90°、180°、270°三种噪声源角度,测试其言语识别率,并对其主观听声感受进行VAS评估。结果 场景识别模块对各类声音场景的识别准确率分别为语音99%±4%,噪声96%±9%,带噪语音94%±12%,纯音乐94%±15%,带人声音乐92%±13%,预测准确度高;5 min内的场景切换次数分别为语音1.1±0.3次,噪声1.4±0.7次,带噪语音1.3±0.5次,纯音乐1.4±0.8次,带人声音乐1.3±0.5次,预测稳定性较高。当噪声来自侧后方而语音来自正前方时,自适应双麦降噪算法ABeam能够在信噪比为5 dB的噪声环境下显著提高受试者的言语识别率(P<0.001),平均言语识别率提升15.92%。尤其是当噪声来自于正后方180°,开启ABeam能够让受试者的言语识别率显著提高28.68%(P<0.01)。结论 智能辅听系统能够帮助人工耳蜗植入者在不同环境下自动选择合适的声音处理策略,提升其言语可懂度和听声效果。
关键词
人工耳蜗;智能辅听系统;声音场景识别;声音处理策略;ABeam
基金项目(Foundation):
浙江省重点研发计划项目(2020C03068);; 浙江省重点企业研究院资助
作者
项丽阳;李娟娟;韩彦;王金剑;杨典;杨婷君;银力;黄穗
参考文献

1 McMillan A,Durai M,Searchfield GD.A survey and clinical evaluation of hearing aid data-logging:a valued but underutilized hearing aid fitting tool[J].Speech,Lang Hear,2017,21(3):162-171.

2 Eichenauer A,Baumann U,St?ver T,et al.Interleaved acoustic environments:impact of an auditory scene classification procedure on speech perception in cochlear implant users[J].Trends Hear,2021,25:1-14.

3 Mauger SJ,Warren CD,Knight MR,et al.Clinical evaluation of the Nucleus 6 cochlear implant system:performance improvements with SmartSound iQ[J].Int J Audiol,2014,53:564-576.

4 Zhou H,Wang N,Zheng N,et al.A new approach for noise suppression in cochlear implants:a single-channel noise reduction algorithm[J].Front Neurosci,2020,14:1-12.

5 Ping L,Wang N,Tang G,et al.Implementation and preliminary evaluation of “C-tone”:a novel algorithm to improve lexical tone recognition in Mandarin-speaking cochlear implant users[J].Cochlear Implants Int,2017,18(5):240-249.

6 Fu QJ,Zhu M,Wang X.Development and validation of the Mandarin speech perception test[J].J Acoust Soc Am,2011,129(6):EL267-EL273.

7 Sivonen V,Willberg T,Aarnisalo AA,et al.The efficacy of microphone directionality in improving speech recognition in noise for three commercial cochlear-implant systems[J].Cochlear Implants Int,2020,21(3):153-159.

8 Büchner A,Schwebs M,Lenarz T.Speech understanding and listening effort in cochlear implant users-microphone beamformers lead to significant improvements in noisy environments[J].Cochlear Implants Int,2020,21(1):1-8.