本文選題：重疊語音檢測(cè) + 高層信息特征　； 參考：《清華大學(xué)學(xué)報(bào)(自然科學(xué)版)》2017年01期

【摘要】：重疊語音是影響說話人分割性能的主要因素之一。該文提出了基于語音高層信息特征的重疊語音檢測(cè)方法以提高說話人分割效果。首先用通用背景模型(universal background model,UBM)提取語音的語言學(xué)高層信息特征,并融合這些特征和Mel頻率倒譜系數(shù)(Mel frequency cepstral coefficient,MFCC)特征建立隱Markov模型(hidden Markov model,HMM)檢測(cè)重疊語音,然后對(duì)處理后的語音進(jìn)行說話人分割。實(shí)驗(yàn)結(jié)果表明:對(duì)于由TIMIT語音庫生成的數(shù)據(jù)集,該方法對(duì)重疊語音檢測(cè)的錯(cuò)誤率比單一采用MFCC特征有顯著降低,而且說話人分割性能有明顯的提高。
[Abstract]:Overlapping speech is one of the main factors that affect the performance of speaker segmentation.In this paper, an overlapping speech detection method based on high level information features is proposed to improve speaker segmentation.Firstly, the general background model universal background model (UBM) is used to extract the high-level linguistic information features of speech, and these features are fused with Mel frequency cepstrum coefficients (Mel frequency cepstral coefficients) to establish a hidden Markov model, hidden Markov model (HMMM), to detect overlapped speech.Then the speech is segmented.Experimental results show that the error rate of overlapping speech detection based on TIMIT speech corpus is significantly lower than that of single MFCC feature, and the performance of speaker segmentation is improved obviously.
【作者單位】： 北京工業(yè)大學(xué)電子信息與控制工程學(xué)院;江蘇師范大學(xué)物理與電子工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(61471014)
【分類號(hào)】：TN912.3

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 王煈;高層信息引導(dǎo)下的道路場(chǎng)景理解技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2012年

，

本文編號(hào)：1761156