<address id="vrn9h"></address>

        <address id="vrn9h"></address>

          <address id="vrn9h"></address><sub id="vrn9h"></sub>

              中文 |

              Newsroom

              Supervised Speech Enhancement Approach Improves Quality of Voice Communication

              Jul 23, 2020

              For voice communication, it is important to suppress background noise without introducing unnatural distortion. Deep learning-based speech enhancement approaches can effectively suppress background noise components.  

              However, in the noise-mismatched condition, unnatural residual noise is generated and it heavily influences speech comfortableness. 

              Recently, researchers from the Institute of Acoustics of the Chinese Academy of Sciences (IACAS) proposed a type of supervised speech enhancement approach with residual noise control for voice communication.  

              Based on artificially maintaining low-level residual noise, researchers dedicated to maximizing noise reduction and minimizing speech distortion jointly, leading to better perceptual comfortableness of enhanced speech. 

              Facing the widely-existing disadvantages of loss functions, researchers introduced multiple adjustable hyper-parameters and derived a generalized loss function.  

              They selected suitable parameter configurations, making the enhanced speech weigh flexibly and effectively between the two objectives. Meanwhile, by introducing low-level background noise, they improved the subjective perceptual quality.  

              Experimental results showed that choosing suitable parameter configurations could make the enhanced speech outperform previous works in terms of both objective metrics and subjective evaluation results. 

              This work could be utilized for noise suppression and speech information extraction in the speech communication devices. 

              The study, published in Applied Sciences, was supported by the National Natural Science Foundation of China. 

              Contact

              ZHOU Wenjia

              Institute of Acoustics

              E-mail:

              A Supervised Speech Enhancement Approach with Residual Noise Control for Voice Communication

              Related Articles
              Contact Us
              • 86-10-68597521 (day)

                86-10-68597289 (night)

              • 86-10-68511095 (day)

                86-10-68512458 (night)

              • cas_en@cas.cn

              • 52 Sanlihe Rd., Beijing,

                China (100864)

              Copyright © 2002 - Chinese Academy of Sciences

              【马德里竞技赞助商-顶盛】一家专业性的体育平台,提供足球直播、篮球直播、体育赛事投注,,投入大量的人力...

              大富豪棋牌app官网

              头头彩票下载

              09电竞平台战绩查询

              杏彩彩票娱乐平台下载一个

              11选5购买平台

              排三预测三天计划

              皇冠棋牌

              99彩票注册平台

              蚂蚁彩票计划平台

              ac彩票平台

              老彩民彩票app下载

              腾达彩票app下载