Hearing AIDS APP design based on deep learning technology

Ji Yan Han, Wei Zhong Zheng, Ren Jie Huang, Yu Tsao, Ying Hui Lai

研究成果: Conference contribution同行評審

3 引文 斯高帕斯(Scopus)

摘要

Hearing loss is a common health issue in an aging society. When the seniors are suffering from hearing losses, it will affect their quality of life drastically. According to the World Health Organization in 2018, the population with hearing loss has reached 466 million and it is estimated that the number of hearing-impaired population will reach 900 million by 2050. Therefore, it is stated clearly that the hearing loss study deserves more attention and effort. For a hearing loss individual, the hearing aid is the most common assistive device to help users to improve the audibility capability. The previous studies indicated that the hearing aids can provide suitable gain in the quiet environment; however, there is still room for improvement in the environment with noise. Due to this issue, this study proposed a real-time speech enhancement system for hearing loss individual improve listening benefits in noisy conditions, based on deep neural network (DNN) technology. More specifically, we embedded the DNN-based SE approach in a smartphone to achieve real-time speech enhancement processing. The preliminary results showed that the proposed system provides benefits for users under noisy listening conditions.

原文English
主出版物標題2018 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面495-496
頁數2
ISBN(電子)9781538656273
DOIs
出版狀態Published - 2 7月 2018
事件11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018 - Taipei, Taiwan
持續時間: 26 11月 201829 11月 2018

出版系列

名字2018 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018 - Proceedings

Conference

Conference11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018
國家/地區Taiwan
城市Taipei
期間26/11/1829/11/18

指紋

深入研究「Hearing AIDS APP design based on deep learning technology」主題。共同形成了獨特的指紋。

引用此