延边大学学报(自然科学版)
延邊大學學報(自然科學版)
연변대학학보(자연과학판)
JOURNAL OF YANBIAN UNIVERSITY(NATURAL SCIENCE EDITION)
2014年
1期
45-48
,共4页
MFCC%k均值聚类%KNN分类%符号化%编辑距离
MFCC%k均值聚類%KNN分類%符號化%編輯距離
MFCC%k균치취류%KNN분류%부호화%편집거리
M FCC%k-means clustering%KNN-classification%symbolization%Levenshtein distance
提出了将语音帧符号化后度量语音相似性的方法。首先,去除语音段中的静音部分,并提取每帧语音的MFCC参数;其次,将MFCC参数进行 k均值聚类和KNN分类,并根据分类结果对语音信号进行符号化;最后,采用编辑距离计算语音段之间的相似性。实验表明,将语音符号化后,音频之间的可区分性更加明显,识别率也有了明显提高。
提齣瞭將語音幀符號化後度量語音相似性的方法。首先,去除語音段中的靜音部分,併提取每幀語音的MFCC參數;其次,將MFCC參數進行 k均值聚類和KNN分類,併根據分類結果對語音信號進行符號化;最後,採用編輯距離計算語音段之間的相似性。實驗錶明,將語音符號化後,音頻之間的可區分性更加明顯,識彆率也有瞭明顯提高。
제출료장어음정부호화후도량어음상사성적방법。수선,거제어음단중적정음부분,병제취매정어음적MFCC삼수;기차,장MFCC삼수진행 k균치취류화KNN분류,병근거분류결과대어음신호진행부호화;최후,채용편집거리계산어음단지간적상사성。실험표명,장어음부호화후,음빈지간적가구분성경가명현,식별솔야유료명현제고。
We presented a method to measure similarity of speech by using frame symbolization .Firstly ,remo-ving silence parts from speech segments ,MFCC coefficients were extracted from each frame .Secondly ,MF-CC coefficients were classified by KNN-classification algorithm in terms of k-means clustering results ,and speech signals to do symbolization processing according to the classification .Finally ,speech similarity was computed by using Levenshtein distance .Experiment results show that frame symbolization makes distinction between different speeches are more obvious ,and recognition rate has improved significantly .