生物医学工程研究2024，Vol.43Issue(1)：62-69,8.DOI:10.19529/j.cnki.1672-6278.2024.01.09
面向人工耳蜗的改进Wave-U-Net算法
Improved Wave-U-Net algorithm for cochlear implants
巩瑾琪 1叶萍 1吴逸凡 1常兆华 1樊伟 2许长建2
作者信息
- 1. 上海理工大学 健康科学与工程学院,上海 200093
- 2. 上海微创天籁医疗科技有限公司,上海 200120
- 折叠
摘要
Abstract
Aim at poor speech perception in noisy environments by cochlear implant users and the inadequacy of existing noise re-duction algorithms,we proposed an improved Wave-U-Net model.By adopting lightweight convolution,introducing attention mecha-nism,improving loss function,and optimizing dataset structure,the noise reduction effect of cochlear implants was enhanced.Using short-time objective intelligibility(STOI),perceptual evaluation of speech quality(PESQ),floating point operations per second(FLOPs),and Params to evaluate the noise reduction effect and complexity of the model,which reached 0.81,2.75,0.83 G,and 1.04 M,respectively.The experimental results showed that our algorithm achieved obvious noise reduction effect while conformed to the specifications of cochlear implant products,improved the speech perception effect of cochlear implant users in complex noise environ-ments.The results provide new possibilities for the improvement of cochlear implant algorithms and can offer better auditory experience for patients with hearing impairment.关键词
人工耳蜗/改进Wave-U-Net/噪声环境/语音感知/语音降噪Key words
Cochlear implant/Improved Wave-U-Net/Noisy environment/Speech perception/Speech noise reduction分类
医药卫生引用本文复制引用
巩瑾琪,叶萍,吴逸凡,常兆华,樊伟,许长建..面向人工耳蜗的改进Wave-U-Net算法[J].生物医学工程研究,2024,43(1):62-69,8.
