Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users

详细信息    查看全文

• 作者：Tobias Goehring^a ; ¹ ; ^{goehring.tobias@gmail.com} ; Federico Bolner^b ; ^c ; ¹ ; Jessica J.M. Monaghan^a ; Bas van Dijk^c ; Andrzej Zarowski^d ; Stefan Bleeck^a
• 关键词：Cochlear implants ; Noise reduction ; Speech enhancement ; Machine learning ; Neural networks
• 刊名：Hearing Research
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：344
• 期：Complete
• 页码：183-194
• 全文大小：1391 K
• 卷排序：344

文摘

An algorithm for improving speech understanding in noise for cochlear implant users is evaluated. Significant improvements were found for stationary and non-stationary noise types. It generalizes to a novel speaker and works over a range of signal-to-noise ratios. The small algorithmic delay makes it suitable for real-time application.