【摘要】：近年來,嵌入式系統(tǒng)的語音識(shí)別系統(tǒng)已經(jīng)廣泛應(yīng)用到智能家居、工業(yè)控制、移動(dòng)終端等領(lǐng)域,正改變著人們的生活。由于語言交流是人們之間最自然的交流方式,基于語音識(shí)別的人機(jī)交互的嵌入式系統(tǒng)越來越成為研究的熱點(diǎn)。然而,現(xiàn)有的語音識(shí)別系統(tǒng)或具有很高的CPU使用率,不能完成其它任務(wù);或具有很大的體積,難以在嵌入式系統(tǒng)使用;或網(wǎng)絡(luò)依賴性太高,在無網(wǎng)絡(luò)條件下僅能完成有限詞匯量的識(shí)別。為了解決這些問題,在嵌入式語音識(shí)別方面還需要對(duì)系統(tǒng)結(jié)構(gòu)進(jìn)行深入的研究。本文提出基于可重構(gòu)的片上語音識(shí)別系統(tǒng),在一定程度上有效緩解了上述矛盾。所作的主要工作如下:首先,本文研究了語音信號(hào)的信號(hào)處理。從信號(hào)處理的角度,討論了在語音識(shí)別過程中用到關(guān)鍵技術(shù)的原理。這包括預(yù)加重、端點(diǎn)檢測、特征提取等技術(shù)。其次,本文介紹了隱馬爾可夫模型的基本原理以及高斯混合模型的基本原理。通過對(duì)隱馬爾可夫模型的三個(gè)問題的論述,特別是高斯混合模型表示的隱馬爾可夫模型的B參數(shù)的詳細(xì)論述,解決了語音識(shí)別系統(tǒng)的訓(xùn)練及識(shí)別的原理問題。再次,本文以ZYNQ7000作為SOC設(shè)計(jì)平臺(tái),構(gòu)建了嵌入式非特定人孤立詞語音識(shí)別系統(tǒng)。在對(duì)ZYNQ7000的可重構(gòu)性研究的基礎(chǔ)上,本文一方面在前有的PC端訓(xùn)練軟件的基礎(chǔ)上,進(jìn)一步將識(shí)別模型改進(jìn)為基于高斯混合模型的隱馬爾可夫模型(GMM-HMM),形成系統(tǒng)驗(yàn)證平臺(tái),為識(shí)別系統(tǒng)提供識(shí)別模板和硬件測試數(shù)據(jù)。這包括對(duì)訓(xùn)練和識(shí)別算法的研究及實(shí)現(xiàn)。還包括將系統(tǒng)中間數(shù)據(jù)轉(zhuǎn)換成易于硬件測試的格式。另一方面,將識(shí)別算法移植到ZYNQ7000平臺(tái),實(shí)現(xiàn)了片上語音識(shí)別系統(tǒng)的構(gòu)建。這包括通過對(duì)識(shí)別流程的評(píng)估,完成對(duì)識(shí)別系統(tǒng)進(jìn)行了軟硬件劃分,并且完成對(duì)語音識(shí)別的關(guān)鍵算法作了適合硬件特性的改進(jìn)。這還包括對(duì)關(guān)鍵計(jì)算單元的硬件重構(gòu),通過硬件邏輯實(shí)現(xiàn)數(shù)字信號(hào)處理中的常見算法。在本文中,主要研究了MFCC計(jì)算單元的重構(gòu)。最后,通過對(duì)系統(tǒng)的識(shí)別率和實(shí)時(shí)性的測試,闡述了采用可重構(gòu)片上語音識(shí)別系統(tǒng)優(yōu)勢以及對(duì)將來工作的展望。
[Abstract]:In recent years, embedded speech recognition system has been widely used in smart home, industrial control, mobile terminals and other fields, is changing people's lives. Because language communication is the most natural way of communication between people, the embedded system based on speech recognition has become more and more popular in the field of human-computer interaction. However, the existing speech recognition system either has a high CPU usage rate, can not accomplish other tasks, or has a large size, so it is difficult to use in embedded system. Or the network dependence is too high, can only complete the limited vocabulary identification under the condition of no network. In order to solve these problems, embedded speech recognition needs to be deeply studied. In this paper, a reconfigurable on-chip speech recognition system is proposed, which effectively alleviates the above contradictions to a certain extent. The main work is as follows: firstly, this paper studies the signal processing of speech signal. From the point of view of signal processing, the principle of key techniques used in speech recognition is discussed. This includes pre-weighting, endpoint detection, feature extraction and other techniques. Secondly, this paper introduces the basic principle of hidden Markov model and Gao Si mixed model. The training and recognition principle of speech recognition system is solved by discussing three problems of Hidden Markov Model, especially the B parameter of Hidden Markov Model represented by Gao Si's mixed model. Thirdly, using ZYNQ7000 as the design platform of SOC, the embedded speech recognition system for isolated words is constructed. On the basis of the research on the reconfiguration of ZYNQ7000, on the one hand, based on the previous PC training software, the recognition model is further improved to the hidden Markov model (GMM-HMM) based on Gao Si's mixed model to form a system verification platform. Provide identification template and hardware test data for identification system. This includes the research and implementation of training and recognition algorithms. It also includes converting the system intermediate data into a format that is easy to test with hardware. On the other hand, the recognition algorithm is transplanted to ZYNQ7000 platform to realize the construction of on-chip speech recognition system. Through the evaluation of the recognition process, the hardware and software partition of the recognition system is completed, and the improvement of the key algorithm of speech recognition is made suitable for the hardware characteristics. It also includes hardware reconfiguration of key computing units and implementation of common algorithms in digital signal processing through hardware logic. In this paper, the reconstruction of MFCC computing unit is studied. Finally, by testing the recognition rate and real-time performance of the system, the advantages of the reconfigurable on-chip speech recognition system and the prospect of future work are discussed.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN912.34

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 賁俊,萬旺根,余小清;基于置信度的非特定人語音識(shí)別拒識(shí)算法的研究[J];計(jì)算機(jī)應(yīng)用研究;2003年07期

，

本文編號(hào)：2445288