Paper ID | F-1-3.1 |
Paper Title |
Speech Enhancement for Optical Laser Microphone With Deep Neural Network |
Authors |
Chengkai CAI, Kenta Iwai, Takanobu Nishiura, Yoichi Yamashita, Ritsumeikan University, Japan |
Session |
F-1-3: Speech Enhancement 1 |
Time | Tuesday, 08 December, 17:15 - 19:15 |
Presentation Time: | Tuesday, 08 December, 17:15 - 17:30 Check your Time Zone |
|
All times are in New Zealand Time (UTC +13) |
Topic |
Speech, Language, and Audio (SLA): |
Abstract |
The development of distant-talking speech measurement systems is drawing attention since it can be used for security and disaster relief. An optical laser microphone that measures the vibration caused by sound using laser beam is suitable for the system. It can capture only the target sound even in a noisy place. However, the sound acquired by the optical laser microphone depends on the irradiated objects, and most of the objects will cause degradation of sound quality. Due to various deteriorations in the sound acquired by the laser microphone, the results of the conventional speech enhancement methods are insufficient. Therefore, in this paper, we propose a speech enhancement method using a two-stage process of noise suppression and acoustic structure reconstruction for optical laser microphones and conduct an objective experiment to evaluate the effectiveness of the proposed method. |