{"title":"A Snoring Signal Enhancement Algorithm Based on OM-LSA and Subspace","authors":"BinYi Lv, Tieqiang Li, Han Yang, Xia Li","doi":"10.1109/ICAICE54393.2021.00042","DOIUrl":null,"url":null,"abstract":"In view of the noise reduction of the snoring signal, a snoring signal enhancement method is proposed in this paper, which is combined with the optimal modified logarithmic spectrum amplitude estimation (OM-LSA) and subspace method. Firstly, the OM-LSA algorithm integrating improved minimum control recursive average (IMCRA) is used for preliminary noise reduction. The method uses short-time window to estimate the minimum value of noise. It uses noise estimation to obtain the optimal spectrum gain function to minimize the mean square error between the actual pure snoring signal power spectrum amplitude and the estimated pure snoring signal power spectrum amplitude to suppress the noise. Then, the subspace method further reduces the noise to make a more compromised choice in suppressing noise and reducing signal distortion. The experimental results show that this method is better than most traditional speech enhancement algorithms in different noise environments and can obtain better snoring signal quality.","PeriodicalId":388444,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAICE54393.2021.00042","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In view of the noise reduction of the snoring signal, a snoring signal enhancement method is proposed in this paper, which is combined with the optimal modified logarithmic spectrum amplitude estimation (OM-LSA) and subspace method. Firstly, the OM-LSA algorithm integrating improved minimum control recursive average (IMCRA) is used for preliminary noise reduction. The method uses short-time window to estimate the minimum value of noise. It uses noise estimation to obtain the optimal spectrum gain function to minimize the mean square error between the actual pure snoring signal power spectrum amplitude and the estimated pure snoring signal power spectrum amplitude to suppress the noise. Then, the subspace method further reduces the noise to make a more compromised choice in suppressing noise and reducing signal distortion. The experimental results show that this method is better than most traditional speech enhancement algorithms in different noise environments and can obtain better snoring signal quality.