本文選題：聲紋識(shí)別 + 小波包變換��； 參考：《哈爾濱理工大學(xué)》2014年碩士論文

【摘要】：本文所研究的聲紋識(shí)別系統(tǒng)主要分為端點(diǎn)檢測(cè)，特征提取和識(shí)別模型三個(gè)部分。端點(diǎn)檢測(cè)部分主要研究了基于線性預(yù)測(cè)倒譜距離和短時(shí)過(guò)零率的雙門限法，實(shí)驗(yàn)證明新的雙門限法能夠解決傳統(tǒng)雙門限法不能檢測(cè)能量低的語(yǔ)音段的問(wèn)題。特征提取部分，采用了美爾倒譜系數(shù)與差分美爾頻率倒譜系數(shù)相結(jié)合的特征參數(shù)，更好的體現(xiàn)了說(shuō)話人的個(gè)性特征。然后對(duì)高斯混合模型進(jìn)行了研究，，提出了分裂法與K均值聚類法相結(jié)合的模型參數(shù)初始化方法，并用高斯混合模型對(duì)兩種端點(diǎn)檢測(cè)算法、特征提取算法和訓(xùn)練方法進(jìn)行了仿真實(shí)驗(yàn)，在純凈的語(yǔ)音環(huán)境下，系統(tǒng)具有良好的識(shí)別效果。 聲紋識(shí)別研究的難點(diǎn)之一，即是在背景噪聲下的識(shí)別系統(tǒng)的研究。雖然在純凈語(yǔ)音環(huán)境下的識(shí)別系統(tǒng)性能很好，但是在噪聲環(huán)境下，識(shí)別率明顯降低。本文運(yùn)用小波變換和小波包變換對(duì)噪聲進(jìn)行了去噪處理實(shí)驗(yàn)，小波包去噪效果明顯優(yōu)于小波變換，然后在小波包常用閾值和折衷閾值的基礎(chǔ)上提出了改進(jìn)的閾值去噪方法，通過(guò)對(duì)語(yǔ)音信號(hào)的對(duì)比仿真實(shí)驗(yàn)，和對(duì)整個(gè)系統(tǒng)的實(shí)驗(yàn)數(shù)據(jù)表明，本文提出的基于小波包改進(jìn)閾值算法很好地去除了噪聲，去噪之后的識(shí)別系統(tǒng)取得了較高的識(shí)別率。最后將算法應(yīng)用在實(shí)際復(fù)雜的噪聲處理中，算法仍然有效地去除噪聲。
[Abstract]:The voiceprint recognition system is mainly divided into three parts: endpoint detection, feature extraction and recognition model.In the end detection part, the double threshold method based on linear predictive cepstrum distance and short time zero crossing rate is studied. The experiment shows that the new double threshold method can solve the problem that the traditional double threshold method can not detect the speech segment with low energy.In the part of feature extraction, the feature parameters of the combination of Mel cepstrum number and differential Mel frequency cepstrum coefficient are adopted, which better reflect the speaker's personality characteristics.Then, the Gao Si mixed model is studied, and the initialization method of the model parameters is proposed, which combines split method and K-means clustering method, and then two endpoint detection algorithms are proposed by the Gao Si mixed model.The simulation results of feature extraction algorithm and training method show that the system has good recognition effect in pure speech environment.One of the difficulties in the research of voiceprint recognition is the research of recognition system under background noise.Although the performance of the recognition system in pure speech environment is very good, the recognition rate is obviously decreased in the noise environment.In this paper, wavelet transform and wavelet packet transform are used to deal with noise. The denoising effect of wavelet packet is obviously better than that of wavelet transform. Then, an improved threshold denoising method is proposed on the basis of common threshold and compromise threshold of wavelet packet.Through the comparison and simulation of speech signal and the experimental data of the whole system, it is shown that the improved threshold algorithm based on wavelet packet can remove the noise very well, and the recognition system after denoising has achieved a high recognition rate.Finally, the algorithm is applied to complex noise processing, and the algorithm is still effective in removing noise.
【學(xué)位授予單位】：哈爾濱理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN912.3

【引證文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前2條

1 張超;語(yǔ)音端點(diǎn)檢測(cè)方法研究[D];大連理工大學(xué);2016年

2 沈蓉;智能門禁系統(tǒng)聲紋識(shí)別中端點(diǎn)檢測(cè)算法研究[D];西安科技大學(xué);2015年

本文編號(hào)：1765837