教師資料查詢 | 類別: 會議論文 | 教師: 謝景棠 Hsieh Ching-tang (瀏覽個人網頁)

標題:SPEECH ENHANCEMENT BASED ON LABEL CONSISTENT K-SVD UNDER NOISY ENVIRONMENT
學年104
學期2
發表日期2016/06/25
作品名稱SPEECH ENHANCEMENT BASED ON LABEL CONSISTENT K-SVD UNDER NOISY ENVIRONMENT
作品名稱(其他語言)
著者Hsieh, Ching-Tang; Chiang, Cheng-Yuan; Chen, Ting-Wen
作品所屬單位
出版者
會議名稱2016 5th International Conference on Computer, Electronics and Data Processing (ICCEDP 2016)
會議地點China, Taiyuan
摘要The sparse algorithm for sparse enhancement is more and more popular issues, recently. In previous research, the sparse algorithm for sparse enhancement will spend much time, so we propose LC K-SVD(Label Consistent K-SVD) to reduce spending time. We focus on the White Gaussian Noise. The experiments show that denoising performance of our proposed method is very closed to sparse algorithm in SNR, LLR, SNRseg and PESQ, even better then it. Our method only need half time then sparse algorithm.
關鍵字Speech enhancement;sparse representations;K-SVD;Label Consistent K-SVD(LCKSVD)
語言英文
收錄於
會議性質國際
校內研討會地點
研討會時間20160625~20160626
通訊作者
國別中國
公開徵稿
出版型式
出處Advances in Computer Science Research
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!