(3.238.235.155) 您好!臺灣時間:2021/05/16 16:52
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:陳功易
研究生(外文):Gong-Yi Chen
論文名稱:結合音源方位估測與語音辨識之智慧型自走車設計
論文名稱(外文):Integrating Design of Sound Orientation Estimation and Speech Recognition in an Intelligent Vehicle
指導教授:練光祐
指導教授(外文):Kuang-Yow Lian
口試委員:陳美勇阮議聰吳德豐曾傳蘆
口試日期:2016-07-27
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:電機工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2016
畢業學年度:104
中文關鍵詞:語音辨識音源方位估測
外文關鍵詞:Speech RecognitionSound Orientation Estimation
相關次數:
  • 被引用被引用:0
  • 點閱點閱:212
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文設計及研製一個具有語音辨識與音源方位估測之智慧型聲音控制系統。當使用者呼叫此系統到自己身邊時,此系統會辨識使用者的語音命令,且同時估算使用者音源的方位,之後系統會控制自走車朝著使用者的方位前進,行進的過程中若遇到障礙物,系統會避開障礙物且持續朝使用者的方向前進。此系統使用Raspberry Pi以及微控制器為主要的控制核心,主要分別用來處理音源方位估測以及語音辨識。音源方位估測的部分本系統使用三個聲音感測器組成一個麥克風陣列,透過Raspberry Pi運算延遲時間差(Time Delay of Arrival, TDOA)演算法,利用每兩個聲音感測器收到聲音的時間延遲差關係估測出12個方位。語音辨識的部分透過微控制器控制EasyVR3模組達到語音辨識以及語音輸出的功能。除此之外,使用超音波以及人體紅外線感測器來達到避障以及鎖定使用者的功能。本論文研製的系統不需使用影像處理的技術也不需透過電腦的運算即可做到語音的辨識以及音源方位估測的功能,除了到使用者身邊的指令外,也可以控制系統做前進、左旋轉、右旋轉以及停止等動作。建立使用者與自走車的連結與互動功能,達到自走車服務使用者的目的。
In this thesis, an automatic vehicle equipped with a smart sound control system for speech recognition and sound orientation estimation is designed and built up. Whenever the user calls the platform, this system recognizes the user’s command and determines the direction of user’s sound. Then, the system drives the automatic vehicle to move towards the user. In case of obstacles en route, the vehicle avoids them and continues to move towards the calculated destination. The main control core in this system comprises of Raspberry Pi and Arduino Uno. In the sound orientation estimation part, this system uses a microphone made up of a series of three sound sensors. By making use of the TDOA (Time Delay of Arrival) calculated by Raspberry Pi, the TDOA relationships among every two sound sensors are used to determine 12 azimuth angles. In the speech recognition, the Easy VR3 module is controlled via the Arduino Uno Controller to achieve speech recognition function. In addition, ultrasonic sensors and physiological IR sensors are utilized to achieve obstacle avoidance and command-giver seeking. The system studied, designed and built in this research requires neither image processing nor calculations by an external computer to perform the above mentioned functions. Besides getting to the command-giver’s spot, the system is also able to drive the vehicle forward, turn it clockwise or anti-clockwise and make it stop. This research creates the interactive function between users and the automatic vehicle. Then, we achieve the service purpose using the automatic vehicle.
摘要 i
Abstract ii
誌謝 iv
目錄 v
表目錄 viii
圖目錄 ix
第一章 序論 1
1.1 研究背景 1
1.2 研究動機與目的 2
1.3 文獻回顧 3
1.4 研究貢獻 5
1.5 論文架構 6
第二章 系統架構 7
2.1 系統架構簡介 7
2.2 音源方位估測系統硬體介紹 8
2.2.1 聲音感測器 8
2.2.2 Raspberry Pi 8
2.3 自走車控制以及語音辨識系統硬體介紹 10
2.3.1 全方向移動自走車 10
第三章 語音辨識與音源方位估測演算法設計 14
3.1 語音辨識系統介紹 14
3.2 音源方位估測法 20
3.2.1 TDOA介紹 20
3.2.2 AMDF方法介紹 21
3.2.3 Ratio AMDF方法介紹 22
3.2.4 最小平方法介紹 23
3.2.5 Cross Correlation方法介紹 24
3.3 音源方位估測系統之實現 25
3.3.1 聲音訊號的擷取 25
3.3.2 NumPy函式庫介紹 29
3.3.3 音源方位估測演算法設計與實現 30
3.3.4 兩訊號之延遲與取樣時間之關係 41
第四章 自走車控制策略設計 43
4.1 自走車之馬達控制 43
4.1.1 馬達控制器 43
4.1.2 自走車控制 44
4.1.3 自走車之任意方位控制 48
4.2 人體紅外線感測 48
4.2.1 人體紅外線感測原理 48
4.2.2 使用者搜尋方法 49
4.3 自走車之避障控制 51
4.3.1 超音波避障原理 51
4.3.2 避障方法 52
第五章 系統整合與實驗結果 55
5.1 系統之溝通與軟硬體整合 55
5.1.1 硬體整合 55
5.1.2 軟體整合與溝通 58
5.2 實驗結果 61
5.2.1 語音辨識後執行一般動作之實驗結果 62
5.2.2 聲源方位估測且尋找使用者的過程中有障礙物之結果 66
5.2.3 聲源方位估測尋找使用者且行進過程無障礙物之結果 69
第六章 結論與未來展望 73
6.1 結論 73
6.2 未來展望 73
參考文獻 75
[1]陳朝陽,智慧型居家機器人之研發,碩士論文,國立成功大學工程科學系,民國92年。
[2]A. V. Gulalkari, D. Sheng, P.S Pratama, H. Kyeong-Kim, G. Sig-Byun and S.Bong-Kim, “Kinect Camera Sensor-Based Object Tracking and Following of Four Wheel Independent Steering Automatic Guided Vehicle Using Kalman Filter,” The 15th International Conference on Control, Automation and Systems, Korea, October, 2015, pp. 1650-1655.
[3]C. Zhao, W. Chen, Z. Zhao and J. Liu, “An RGBD Data Based Vehicle Detection Algorithm for Vehicle Following Systems,” The 8th Conference on Industrial Electronics and Applications, China, 2013, pp. 1506-1511.
[4]T. Ishi, S. Matsuda, T. Kanda, T. Jitsuhiro, H. Ishiguro, S. Nakamura and N. Hagita, “A Robust Speech Recognition System for Communication Robots in Noisy Environments,” IEEE Transactions on Robotics, vol. 24, issue 3, 2008, pp. 759-763.
[5]Y. Xing and W. Chen, “Design of Speech Recognition Robot Based on MCU,” The 4th International Conference on Intelligent Human-Machine Systems and Cybernetics, China, 2012, pp253-256.
[6]H. Lee, S. Chang, D. Yook and Y. Kim, “A Voice Trigger System Using Keyword and Speaker Recognition for Mobile Devices,” IEEE Transactions on Consumer Electronics, vol. 55, issue 4, 2009, pp. 2377-2384.
[7]H. V. Hamme, “Robust Speech Recognition Using Cepstral Domain Missing Data Techniques and Noisy Masks, ” IEEE International Conference on Acoustics, Speech, and Signal Processing, 2004, pp. 213-216.
[8]P. Ding and L. He, “Robust Mandarin Speech Recognition in Car Environments for Embedded Navigation System,” IEEE Transactions on Consumer Electronics, vol. 54, issue 2, 2008, pp. 584-590.
[9]I. C. Yoo and D. Yook, “Automatic Sound Recognition for the Hearing Impaired,” IEEE Transactions on Consumer Electronics, vol. 54, issue 4, 2008, pp. 2029-2036.
[10]A. K. Paul D. Das and M.M Kamal, “Bangla Speech Recognition System Using LPC and ANN,” Seventh International Conference on Advances in Pattern Recognition, Kolkata, 2009, pp. 171-174.
[11]W. Junqin and Y. Junjun, “An Improved Arithmetic of MFCC in Speech Recognition System,” International Conference on Electronics, Communications and Control, Zhejiang, 2011, pp.719-722.
[12]H. Y. Cho and Y. H Oh, “On the Use of Channel-Attentive MFCC for Robust Recognition of Partially Corrupted Speech,” IEEE Signal Processing Letters, vol. 11, issue 6, 2004, pp. 581-584.
[13] W. H. Abdulla, D. Chow and G. Sin, “Cross-Words Reference Template for DTW-Based Speech Recognition Systems,” Conference on Convergent Technologies for the Asia-Pacific Region, 2003, pp. 1576-1579.
[14]H. Kaprykowsky and X. Rodet, "Globally Optimal Short-Time Dynamic Time Warping, Application to Score to Audio Alignment", International Conference on Speech and Signal Processing, 2006, pp. V.
[15]L. R. Rabiner, "A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition", Proc. IEEE, vol. 77, no.2, 1989, pp.257-286.
[16]K. Kanagisawa, A. Ohya and S. Yuta, “An Operator Interface for an Autonomous Mobile Robot Using Whistle Sound and a Source Direction Detection System,” Industrial Electronics, Control, and Instrumentation, 1995, pp. 1118-1123.
[17]DFROBOT Company, http://www.dfrobot.com/
[18]Raspberry Pi介紹,https://en.wikipedia.org/wiki/Raspberry_Pi
[19]R. Diamant, “Clustering Approach for Detection and Time of Arrival Estimation of Hydrocoustic Signals,” IEEE Sensors Journal, vol. 16 issue 13, 2016, pp. 5308-5318.
[20]C. K. Chen and W. A. Gardner, “Signal-Selective Time-Difference of Arrival Estimation for Passive Location of Man-made Signal Sources in Highly Corruptive Environments.” IEEE Transactions on Signal Processing, vol. 40 issue. 5, 1992, pp1185-1197.
[21]M. Ross, H. Shaffer, A. Cohen, R. Freudberg and H. Manley, “Average Magnitude Difference Function Pitch Extractor,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 22, issue 5, 1974, pp. 353-362.
[22]涂莎莉,二維空間的音源定位 : 時域方法的實作與探討,碩士論文,國立清華大學資訊工程所,2005。
[23]F. Reed, P. Feintuch and N. Bershad, “Time Delay Estimation Using the LMS Adaptive Filter--Static Behavior,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 29, issue 3, 2003, pp. 561-571.
[24]J. A. Wall, T. M. McGinnity and L. P. Maguire, “A Comparison of Sound Localization Techniques Using Cross-Correlation and Spiking Neural Networks for Mobile Robotics,” International Joint Conference on Neural Networks, San Jose, 2011, pp. 1981-1987.
[25]W. A. Gardner and C. M. Spooner, “Comparison of Autocorrelation and Cross-Correlation Methods for Signal-Selective TDOA Estimation,” IEEE Transactions on Signal Processing, vol. 40 issue 10, 2002, pp. 2606-2608.
[26]MICROCHIP, http://www.microchip.com/wwwproducts/en/MCP3008
[27]Datasheet of MCP3008, https://cdn-shop.adafruit.com/datasheets/MCP3008.pdf
[28]NumPy, http://www.numpy.org/
[29]Pololu Maestro Servo Controller User’s Guide, https://www.pololu.com/docs/pdf/0J40/maestro.pdf
[30]Pyroelectric Infrared Radial Sensor, https://moderndevice.com/wp-content/uploads/2010/11/330600005.pdf
[31]SensorWiki, http://ap.urpi.fei.stuba.sk/sensorwiki/index.php/Acrob015
電子全文 電子全文(網際網路公開日期:20210823)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top