基於RM距離量測之語料獨立語者辨識系統

淡江大學機構典藏 > 工學院 > 電機工程學系暨研究所 > 學位論文 > Item 987654321/111455

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/111455

題名:	基於RM距離量測之語料獨立語者辨識系統
其他題名:	Speaker recognition with independent corpus based on RM distance measure
作者:	江正元;Chiang, Cheng-Yuan
貢獻者:	淡江大學電機工程學系碩士班謝景棠
關鍵詞:	語音增強;稀疏表示;黎曼距離;歐基理德距離;Speech enhancement;sparse representations;K-SVD;Label Consistent K-SVD (LC K-SVD);Riemannian Distance;MFCC;euclidean distance
日期:	2016
上傳時間:	2017-08-24 23:53:16 (UTC+8)
摘要:	在辨識人的身分這方面，語音一直是滿熱門的研究方向。近幾年來，學者們陸續提出在白色雜訊環境與彩色雜訊環境下語者辨識的研究。為了提高LLR、PESQ、SNR 與SNRseg等的評估品質，雜訊去除導入了稀疏表示演算法，但花費時間長。所以我們提出一致性標籤KSVD 稀疏編碼，來縮短處理時間。目前語者辨識系統大多使用歐基理德距離來計算特徵的距離，我們的目標是短語料長度與語料獨立，這使高辨識精確度更難達成。我們提出黎曼距離(Riemannian Distance)取代歐基理德距離，但我們的實驗結果顯示，歐基理德距離遠勝於黎曼距離。本論文的實驗使用波形、MFCC與MFCC平滑化頻譜特徵搭配RD、ED來進行語者識別實驗。 The speaker recognition is always a hot topic in the research field. Technologies of speaker recognition under white and color noisy environments have been proposed in recent years. Sparse representation algorithm has been introduced into noise filtering for improving the assessments of speech quality, such as SNR, SNRseg, LLR and PESQ, but the cost time is lengthy. So we employ Label Consistent K-SVD sparse coding (LC-KSVD) to de-noise speech data and decrease processing time. Speaker recognition systems almost use Euclidean distance to compute the distance between features, currently. Our goal is to have short corpus and independent corpus, which makes it more difficult to achieve high recognition accuracy. We propose Riemannian distance replace Euclidean distance, but our experimental results show that Euclidean distance is superior than Riemannian distance. We use waveform, MFCC and MFCC smoothing spectrum with RD and ED for speaker recognition experiment in this paper.
顯示於類別:	[電機工程學系暨研究所] 學位論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	161	檢視/開啟

在機構典藏中所有的資料項目都受到原著作權保護.

TAIR相關文章

資料載入中.....