【摘要】：隨著機(jī)器人技術(shù)的快速發(fā)展以及社會(huì)需求的不斷增加,清潔、安保、陪護(hù)及康復(fù)等服務(wù)機(jī)器人已經(jīng)逐步走入大眾日常生活。為了方便用戶使用,本文基于實(shí)驗(yàn)室自主研發(fā)的一款家庭智能陪護(hù)機(jī)器人,研究設(shè)計(jì)了一套機(jī)器人語(yǔ)音控制系統(tǒng),使得用戶能夠以一種最為親切自然的方式與機(jī)器人進(jìn)行交互。本文在完成整體方案設(shè)計(jì)的基礎(chǔ)上,對(duì)系統(tǒng)涉及的聲源定位和語(yǔ)音識(shí)別兩個(gè)技術(shù)環(huán)節(jié)進(jìn)行了重點(diǎn)研究。聲源定位方面,本文在比較分析經(jīng)典聲源定位算法的基礎(chǔ)上,選取一種基于到達(dá)時(shí)延的廣義互相關(guān)法(GCC:Generalized CrossCorrelation)定位算法。針對(duì)該算法在噪聲和回響較大環(huán)境中效果不夠理想的問(wèn)題,對(duì)其進(jìn)行了改進(jìn),增加一個(gè)PHAT加權(quán)函數(shù),對(duì)頻譜信號(hào)進(jìn)行處理;同時(shí)引入一種拋物線插值算法,在不提高采樣頻率的前提下,有效提高了空間搜索定位精度。此外,本文還完成了麥克風(fēng)陣列的拓?fù)浣Y(jié)構(gòu)設(shè)計(jì)以及麥克風(fēng)、聲卡等硬件的選型工作。語(yǔ)音識(shí)別方面,本文采用Kaldi開源語(yǔ)音識(shí)別開發(fā)平臺(tái),基于準(zhǔn)備的訓(xùn)練數(shù)據(jù)及腳本,進(jìn)行了單音子、三音子模型及改進(jìn)算法模型的訓(xùn)練,并對(duì)其中涉及的HMM模型、基于加權(quán)有限狀態(tài)機(jī)(WFST)的靜態(tài)空間網(wǎng)絡(luò)等理論進(jìn)行了研究,針對(duì)其中的核心問(wèn)題提出了相應(yīng)的解決方法。通過(guò)語(yǔ)音識(shí)別精度測(cè)試實(shí)驗(yàn),對(duì)各個(gè)模型的識(shí)別精度進(jìn)行比較,最終確定系統(tǒng)采用基于三音子的LSM語(yǔ)音識(shí)別模型。最后,本文制定了上下位機(jī)通信協(xié)議,搭建了語(yǔ)音控制系統(tǒng)實(shí)驗(yàn)平臺(tái),在機(jī)器人運(yùn)動(dòng)控制中,針對(duì)控制精度不高的問(wèn)題,采用了一種PID控制同模糊控制融合的控制策略。在此基礎(chǔ)上,進(jìn)行了聲源定位、自主轉(zhuǎn)向以及語(yǔ)音指令識(shí)別并實(shí)時(shí)響應(yīng)的相關(guān)測(cè)試。大量的實(shí)驗(yàn)結(jié)果及初步的應(yīng)用表明,本文設(shè)計(jì)的陪護(hù)機(jī)器人語(yǔ)音控制系統(tǒng)具有較高的定位和指令識(shí)別精度,可以滿足陪護(hù)機(jī)器人在家庭環(huán)境中的使用需求。
[Abstract]:With the rapid development of robot technology and the increasing demand of society, cleaning, security, escort and rehabilitation service robots have gradually entered the daily life of the public. For the convenience of users, this paper designs a robot voice control system based on a home intelligent escort robot, which is developed independently by the laboratory, which enables the user to interact with the robot in a most friendly and natural way. On the basis of the overall scheme design, this paper focuses on the two technical links of sound source location and speech recognition involved in the system. In the aspect of acoustic source location, based on the comparison and analysis of classical acoustic source localization algorithms, a generalized cross-correlation (GCC:Generalized CrossCorrelation) localization algorithm based on arrival delay is selected. In order to solve the problem that the effect of the algorithm is not ideal in the environment of high noise and reverberation, an PHAT weighting function is added to process the spectrum signal, and a parabola interpolation algorithm is introduced. On the premise of not increasing the sampling frequency, the accuracy of spatial search and location is improved effectively. In addition, the topology design of microphone array and the hardware selection of microphone and sound card are also completed. In the aspect of speech recognition, this paper uses the Kaldi open source speech recognition development platform, based on the training data and script, carries on the training of monosyllabic, tri-phonon and improved algorithm model, and the HMM model involved in it. The theory of static space network based on weighted finite state machine (WFST) is studied, and the corresponding solutions to the core problems are proposed. The recognition accuracy of each model is compared by testing the accuracy of speech recognition. Finally, the LSM speech recognition model based on triphonon is adopted in the system. Finally, the communication protocol of upper and lower computer is established, and the experimental platform of speech control system is built. In order to solve the problem of low control precision in robot motion control, a control strategy combining PID control with fuzzy control is adopted. On this basis, the sound source location, autonomous steering, speech command recognition and real-time response are tested. A large number of experimental results and preliminary applications show that the speech control system designed in this paper has a high accuracy of positioning and instruction recognition, and can meet the needs of the accompanying robot in the home environment.
【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP242

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉曉峰;張雪英;Zizhong John Wang;;Logistic核函數(shù)及其在語(yǔ)音識(shí)別中的應(yīng)用[J];華南理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2015年05期

2 魏鮮明;徐林森;曹凱;駱敏舟;;足式水上行走機(jī)器人智能控制方法設(shè)計(jì)[J];機(jī)器人;2014年01期

3 朱國(guó)騰;孫偉;;基于模板匹配的快速語(yǔ)音關(guān)鍵詞檢出方法[J];計(jì)算機(jī)應(yīng)用;2013年11期

4 韓文靜;李海峰;阮華斌;馬琳;;語(yǔ)音情感識(shí)別研究進(jìn)展綜述[J];軟件學(xué)報(bào);2014年01期

5 劉月嬋;何元安;商德江;尚大晶;孫超;;高精度球面陣聚焦聲源定位方法研究[J];聲學(xué)學(xué)報(bào);2013年05期

6 王磊;郝潤(rùn)科;趙龍;邱銀;劉源;;基于DSP的車載語(yǔ)音識(shí)別系統(tǒng)設(shè)計(jì)[J];信息技術(shù);2013年06期

7 早克熱·卡德爾;艾山·吾買爾;吐爾根·依布拉音;帕里旦·吐爾遜;吳小川;;混合策略的維吾爾語(yǔ)名詞詞干提取系統(tǒng)[J];計(jì)算機(jī)工程與應(yīng)用;2013年01期

8 孫林慧;楊震;季云云;葉蕾;;基于過(guò)完備線性預(yù)測(cè)字典的壓縮感知語(yǔ)音重構(gòu)[J];儀器儀表學(xué)報(bào);2012年04期

9 左敏;曾廣平;涂序彥;魏偉;;基于平行進(jìn)化的機(jī)器人智能控制研究[J];計(jì)算機(jī)仿真;2011年08期

10 梁瑞宇;趙力;奚吉;張學(xué)武;王青云;;基于聽覺仿生和壓縮感知的助聽器聲源定位方法[J];儀器儀表學(xué)報(bào);2011年06期

相關(guān)碩士學(xué)位論文 前2條

1 王君培;基于麥克風(fēng)陣列的近場(chǎng)聲源定位與跟蹤[D];西南交通大學(xué);2014年

2 熊世富;集外詞的語(yǔ)音檢索方法研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2014年

，

本文編號(hào)：2256184