Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/7519
標題: 語音辨識研究及應用於自走車控制
A Study of Text Dependent Speaker Recognition And its Application to Automobile control
作者: 施平輝
Shie, Pyng-Huei
關鍵字: Speech Recognition;語音辨識;Hidden Markov Models;Viterbi Algorithm;Feature extiation;隱藏式馬可夫模型;維特比演算法;特徵值擷取
出版社: 電機工程學系所
引用: 1. Rabiner L. R., "A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition," Proc. IEEE, Vol. 77, No. 2, pp. 283-284, (1989). 2. Tebelskis J., "Speech Recognition using Neural Networks," Ph.D. dissertations, Carnegie Mellon University, Pittsburgh, Pennsylvania, pp. 15-26, (1995). 3. 王小川, 「語音信號處理」, 全華科技, pp.1-7~1-13, (2004) 4. 李東隆, 「動態時間校準於聲控選單環境控制系統之應用」, 碩士論文, 國立中興大學電機工程研究所, 台中, (2002) 5. 張育波, 「特定文字的語者辨認之研究, 」, 碩士論文, 國立中興大學 電機工程研究所, 台中, (2002) 6. Phan T. T. and Soong T., "Text-Independent Speaker Identification," (1999). 7. Hsieh C. T., Lai E. and Wang Y. C., "Robust Speaker Identification System Based on Wavelet Transform and Gaussian Mixture Model," Journal of Information Science and Engineering 19, pp. 267-282, (2003). 8. Augustine Tsai Q. L. and Kim W.G., "A Language Independent Personal Voice Controller with Embedded Speaker Verification," In 6th European Conf. Speech Communication & Technology Proc., Budapest, Hungary, Vol. 3, pp. 1207-1210, (1999). 9. Becchetti C. and Ricotti L. P., "Speech Recognition Theory and C++ Implementation," Fondazione Ugo Bordoni, Rome, Italy. 10. Mammone R. J., Zhang X. and Ramachandran R. P., "Robust speaker recognition: A feature based approach," IEEE Signal Processing Mag. ,Vol. 13, pp.58-71, (1996). 11. Yuan Z. X., Xu B. L. and Yu C. Z., "Binary quantization of feature vectors for robust text-independent speaker identification," IEEE Tran. On Speech and Audio Processing, Vol. 7, No. 1, (1990). 12. Kermorvant C., "A comparison of noise reduction techniques for robust speech recognition," IDIAP-RR 99-10, (1999). 13. Reynolds D. A., and Rose R. C., "Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models," IEEE Tran. On Speech and Audio Processing, Vol. 3, No. 1, (1995). 14. 陳明熒, "PC電腦語音辨認實作," 旗標出版,(1994). 15. Tokuda K., "HMM-Based Speech Synthesis toward Human-like Talking 64 Machines," Nagoya Institute of Technology, Japan. 16. Abdulla W. H. and Kasabov, "The Concepts of Hidden Markov Model in Speech Recognition," Technical Report TR99/09, N. K. Department of Knowledge Engineering Lab Information Science Department University of Otago New Zealand, (1999). 17. 楊鎮光,「Visual Basic 與語音辨識」,松崗圖書, pp. A-8~A-16, (2002).
摘要: 
儘管隱藏式馬可夫模型(HMMs)有著幾個做語音辨識時在假設上的弱
點,但它仍提供一個相當可靠的方法應用於語音辨識系統。本論文的語音辨
識系統使用隱藏式馬可夫模型並結合語音信號的前置處理以及特徵值擷取
技術,再以維特比演算法來做在特定文字的語音模型的訓練及辨識。首先,
用來控制自走車的特定語音命令實驗中,依文字分個數為單字語音,雙字語
音及參字語音,以做為實作語音控制應用時之參考。實驗結果顯示選擇適當
的命令文字及狀態數可得相當高的辨識率;反之,過多的狀態數設定反而會
降低其辨識率。最後,探討如何整合語音辨識技術與相關硬體控制技術應用
於自走車控制。本論文將前述的實驗結果結合即時錄音的方式,將辨識結果
透過USB I/O 介面卡傳送到RF 模組,以無線的方式來傳送命令到由MCS-51
程式控制的自走車。結果顯示本論文所開發之系統具有實用價值。

The Hidden Markov Models (HMMs) provide a highly reliable approach which
can be applied in speech recognition. In this thesis, HMMs, front-end signal processing
technique, and feature extraction technique are used to form a speech recognition
system. Besides, Viterbi algorithm is utilized in an acoustic model and the result can be
used as a threshold for speech recognition. In the experiment of text dependent
commands for control the automobile, the texts are divided into three categories. There
are single-word, two-words, and three-words for the references of speech control
commands. Experimental results show that the selection of suitable text command and
state-numbers can considerably increase the recognition rate; on the contrary uses too
many state-numbers could decrease the recognition rate. We use the speech recognition
techniques and implement on correlative hardware automobile control system. The
speech commands are recorded real time, and the speech recognizing results are
transmitted from RF module through USB I/O interface card and then into the
automobile control system. The outcomes demonstrate that the speech recognition
system is valuable for practical applications.
URI: http://hdl.handle.net/11455/7519
其他識別: U0005-1608200712310500
Appears in Collections:電機工程學系所

Show full item record
 
TAIR Related Article

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.