计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2010年
10期
113-114,152
,共3页
小波变换%维纳滤波%改进的最大分类错误
小波變換%維納濾波%改進的最大分類錯誤
소파변환%유납려파%개진적최대분류착오
wavelet transform%Wiener filtering%Modified Maximum Classification Error(MMCE)
将小波变换和维纳滤波结合起来对语音进行去噪和MMCE对说话人进行识别.说话人识别近来的关注点主要集中在子带处理的使用上.通过三尺度的Daubechiea小波把输入含噪信号分解于不同子带中,然后在各个子带分别通过维纳滤波去噪,再把各个子带的输出通过小波重构恢复信号,最后通过Mel滤波器组把小波系数转换成MFCC(美尔倒谱系数).提出了一种改进的MCE模型去减少计算量,并进而提高运算速度.实验结果显示:提出的方法减少了计算量,而且提高了系统的辨认率.
將小波變換和維納濾波結閤起來對語音進行去譟和MMCE對說話人進行識彆.說話人識彆近來的關註點主要集中在子帶處理的使用上.通過三呎度的Daubechiea小波把輸入含譟信號分解于不同子帶中,然後在各箇子帶分彆通過維納濾波去譟,再把各箇子帶的輸齣通過小波重構恢複信號,最後通過Mel濾波器組把小波繫數轉換成MFCC(美爾倒譜繫數).提齣瞭一種改進的MCE模型去減少計算量,併進而提高運算速度.實驗結果顯示:提齣的方法減少瞭計算量,而且提高瞭繫統的辨認率.
장소파변환화유납려파결합기래대어음진행거조화MMCE대설화인진행식별.설화인식별근래적관주점주요집중재자대처리적사용상.통과삼척도적Daubechiea소파파수입함조신호분해우불동자대중,연후재각개자대분별통과유납려파거조,재파각개자대적수출통과소파중구회복신호,최후통과Mel려파기조파소파계수전환성MFCC(미이도보계수).제출료일충개진적MCE모형거감소계산량,병진이제고운산속도.실험결과현시:제출적방법감소료계산량,이차제고료계통적변인솔.
The wavelet transform and Wiener filtering are combined in order to de-noise and Modified Maximum Classification Error (MMCE) is used for speaker recognition.Noisy signals are decomposed into different subband by Oaubechies wavelet of three sizes.Then these signals are de-noised by Wiener filter in every subband.The output of every subband is resumed by wavelet reconstruction.Finally wavelet coefficient is transformed into MFCC.A kind of modified MCE model to decrease computer multiplications and further to enhance computer velocity is proposed.Experiment result shows that the proposed method can decrease the computation multiplications and improve the identification rate of the system.
