本文選題：麥克風(fēng)陣列 + 語音識別��； 參考：《遼寧工業(yè)大學(xué)》2014年碩士論文

【摘要】：語音識別屬于人工智能和語音處理領(lǐng)域，它是讓機(jī)器聽懂人類的語言，并按照人的命令去執(zhí)行相應(yīng)的操作。目前單通道語音識別發(fā)展迅速，識別效果較好。然而，存在靈活性差、需要佩戴麥克風(fēng)、限制說話人活動等缺點(diǎn)。麥克風(fēng)陣列正好能克服上述單通道語音識別的缺點(diǎn)，，因此，近幾年麥克風(fēng)陣列語音識別逐漸成為研究熱點(diǎn)。 論文在綜述國內(nèi)外語音識別技術(shù)研究進(jìn)展的基礎(chǔ)上，系統(tǒng)分析了目前語音識別存在的問題；闡述了語音信號預(yù)處理的理論基礎(chǔ)，包括采樣量化、分幀加窗、端點(diǎn)檢測等；詳細(xì)分析了特征參數(shù)提取常用的參數(shù)梅爾倒譜系數(shù)；研究了HMM模型的三個基礎(chǔ)算法以及語音識別中基元的選擇和狀態(tài)數(shù)的確定；給出了HMM模型在應(yīng)用中存在的問題及解決辦法。 針對單通道語音識別在實(shí)際環(huán)境中識別效果不理想的問題，論文首先提出一種基于多通道選擇的陣列語音識別方法。該方法針對實(shí)際封閉環(huán)境，構(gòu)建時延補(bǔ)償后陣列信號相關(guān)矩陣，并對其進(jìn)行子空間分解。在信號子空間下，采用基于歸一化多路互相關(guān)系數(shù)的通道選擇方法，去掉相關(guān)性較小的通道、選擇互相關(guān)系數(shù)最大的通道組成新麥克風(fēng)陣列，進(jìn)而經(jīng)過波束形成得到輸出信號；最后，通過語音識別器得到識別結(jié)果。在此基礎(chǔ)上考慮到語音識別不僅是一個信號處理問題，而是一個模型判別問題。因此，陣列波束形成和語音識別聯(lián)合處理，將語音識別系統(tǒng)中的信息運(yùn)用到前端的陣列處理中，用共軛梯度算法找到使正確假設(shè)似然概率最大的濾波器系數(shù)，應(yīng)用到語音識別器得到識別結(jié)果。仿真實(shí)驗(yàn)結(jié)果表明，這些方法不僅減少了陣元數(shù)目，降低了計算量，而且加強(qiáng)了對識別有利的信息，提高了識別率，在復(fù)雜聲學(xué)環(huán)境下具有較好的魯棒性。
[Abstract]:Speech recognition belongs to the field of artificial intelligence and speech processing , it is to let the machine understand human language and carry out corresponding operation according to the human order . At present , the single - channel speech recognition is developed rapidly and the recognition effect is good . However , the microphone array can overcome the disadvantages of single - channel speech recognition , so the speech recognition of microphone array has become a hot spot in recent years .

On the basis of summarizing the research progress of speech recognition at home and abroad , this paper systematically analyzes the existing problems of speech recognition .
The theoretical basis of speech signal preprocessing is described , including sampling quantization , sub - frame windowing , endpoint detection , etc .
The parameter Mel cepstrum coefficient commonly used in extracting characteristic parameters is analyzed in detail .
The three basic algorithms of HMM and the determination of the number of elements in speech recognition are studied .
The problems and solutions of HMM model in application are given .

An array speech recognition method based on multi - channel selection is proposed for single - channel speech recognition in real environment . The method is based on the real - enclosed environment , constructs delay - compensated array signal correlation matrix and subspace decomposition . Under the subspace of signal subspace , the channel selection method based on the normalized multi - channel correlation number is adopted to remove the channel with smaller correlation , and the channel with the largest correlation number is selected to form a new microphone array , and then the output signal is obtained through the beam forming ;
In the end , the recognition result is obtained by the speech recognizer . Based on this , the speech recognition is not only a signal processing problem , but a model discrimination problem . Therefore , the array beam forming and speech recognition combined processing are used to apply the information in the speech recognition system to the array processing of the front end . The result of recognition is obtained by using the conjugate gradient algorithm . The simulation results show that these methods not only reduce the number of elements , reduce the calculation amount , but also enhance the recognition favorable information , improve the recognition rate and have better robustness in the complex acoustic environment .
【學(xué)位授予單位】：遼寧工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TN912.34

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 曾孝平;趙鐵軍;韓慶文;;基于信號噪聲子空間的OFDM信道估計[J];重慶大學(xué)學(xué)報(自然科學(xué)版);2007年09期

2 劉超;莊圣賢;;高脈沖噪聲壞境中雙門限法語音端點(diǎn)檢測研究[J];電子科技;2013年04期

3 榮薇;陶智;顧濟(jì)華;趙鶴鳴;;基于改進(jìn)LPCC和MFCC的漢語耳語音識別[J];計算機(jī)工程與應(yīng)用;2007年30期

4 何玨;劉加;;漢語連續(xù)語音中HMM模型狀態(tài)數(shù)優(yōu)化方法研究[J];中文信息學(xué)報;2006年06期

5 趙賢宇,王作英;用于語音識別的魯棒自適應(yīng)麥克風(fēng)陣列算法[J];清華大學(xué)學(xué)報(自然科學(xué)版);2004年10期

6 劉明宇;高曉晶;;ANN/HMM混合模型中狀態(tài)數(shù)的自適應(yīng)確定方法研究[J];自動化技術(shù)與應(yīng)用;2009年07期

7 張奕;殷福亮;;混響和空間噪聲環(huán)境下的魯棒時延估計方法[J];信號處理;2009年08期

本文編號：2039801