SPEECH ENHANCEMENT BASED ON SPARSE THEORY UNDER NOISY ENVIRONMENT | |
---|---|
學年 | 103 |
學期 | 2 |
發表日期 | 2015-07-18 |
作品名稱 | SPEECH ENHANCEMENT BASED ON SPARSE THEORY UNDER NOISY ENVIRONMENT |
作品名稱(其他語言) | |
著者 | Hsieh, Ching-Tang;Chen, Yan-heng;Chen, Ting-Wen;Chen, Li-Ming |
作品所屬單位 | 電機工程學系暨研究所 |
出版者 | Academy of Taiwan Information Systems Research (ATISR) |
會議名稱 | International Conference on Internet Studies 2015 (NETs 2015) |
會議地點 | Tokyo, Japan |
摘要 | Recently, the sparse algorithm for sparse enhancement is more and more popular issues. In this paper, we classify the process of the sparse theory to enhance speech signal into two parts, one is for dictionary training part and the other is signal reconstruction part. We focus on the White Gaussian Noise. Clean speech dictionary D is trained by K-SVD algorithm. The orthogonal matching pursuit(OMP) algorithm is used to obtain the sparse coefficients X of clean speech dictionary D. Denoising performance of the experiments shows that our proposed method is superior than other methods in SNR, LLR, SNRseg and PESQ. |
關鍵字 | Speech enhancement, sparse representations, K-SVD, discrete cosine transform (DCT), orthogonal matching pursuit (OMP) |
語言 | en_US |
收錄於 | |
會議性質 | 國際 |
校內研討會地點 | |
研討會時間 | 20150718~20150719 |
通訊作者 | Chen, Ting-Wen |
國別 | JPN |
公開徵稿 | Y |
出版型式 | 電子版 |
出處 | International Conference on Internet Studies (NETs 2015) |
相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/103467 ) |