(34.201.11.222) 您好!臺灣時間:2021/02/25 05:22
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:楊萬興
研究生(外文):Wan-Hsing Yang
論文名稱:語者調適在台灣方言辨識之研究
論文名稱(外文):A Study of Speaker Adaptation on Automatic Taiwanese Dialect Identification
指導教授:張文輝
指導教授(外文):Wen-Whei Chang
學位類別:碩士
校院名稱:國立交通大學
系所名稱:電信工程系
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:1999
畢業學年度:87
語文別:中文
論文頁數:72
中文關鍵詞:HMM辨識方言辨識語者調適碼書調適
外文關鍵詞:Chinese-dialect identificationCMSMAPMLLRcodebook adaptation
相關次數:
  • 被引用被引用:1
  • 點閱點閱:143
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
本論文之研究目的在於探討語者差異性對於方言辨識所造成的影響,並針對方言辨識需求而提出一種解決語者不匹配問題的調適架構。主要研究對象為台灣地區三種主要方言-北京話、河洛話及客家話,目標是將多語者模式推展至不特定語者模式。本論文初步採用一種雙層的HMM辨識架構,以獲取方言間存在之音律及聲學差異性作為鑑別之依據,並試圖利用語音辨認中常見之語者補償技術以消除語者不匹配問題。然而,方言辨識中的語者問題並未於這些技術應用之後而獲得解決。於是,我們轉而朝向發展另一種基於向量量化之方言辨識架構,以利於語者調適的有效實現。雖然此辨識架構本質上僅利用了方言中的聲學資訊,但其對於多語者模式下的效能卻直逼雙層HMM的辨識架構。此外經由一簡單的碼書調適之後,對於新測試語者的辨識率有了非常顯著的提升。
Previous work on automatic Chinese-dialect identification using an acoustic-phonotactic model allows the system to differentiate three dialects from each other in a multi-speaker (MS) environment. However, as we extend the task to the speaker-independent (SI) mode, the well-trained identifier suffers from serious degradation due to the mismatch between the training and the testing conditions. In order to overcome this problem, several well-developed solutions such as CMS, spectral transform, MAP, and MLLR were used. However, the experimental results indicate that such speaker compensation schemes developed for speech recognition are less successful. We speculate that the use of speaker compensation may destroy the discriminability of acoustic-phonotactic model. Recognizing this, an acoustic-based VQ-distortion identifier together with codebook adaptation is developed to alleviate the speaker mismatch problem. Simulation results indicate that a VQ-distortion identifier can easily extend to SI system with little degradation.
中文摘要I
ABSTRACTII
誌謝III
目錄IV
圖目錄VI
表目錄VII
第一章緒論1
1.1研究動機與方向1
1.2章節概要2
第二章台灣方言基本特性3
2.1標音方式3
2.2各方言的語音性質4
2.2.1不考慮聲調之聲母及韻母5
2.2.2不考慮聲調之聲、韻母組合8
2.2.3聲調9
第三章方言辨識的基本架構10
3.1語音處理基本技術10
3.1.1特徵參數11
3.1.2 隱藏式馬可夫模型13
3.2方言辨識系統16
3.3語音資料的搜集19
3.4實驗結果與討論21
第四章語者不匹配問題之解決方案29
4.1相關研究調查29
4.2實驗結果與討論36
第五章基於向量量化之方言辨識45
5.1基本架構45
5.1.1VQ/DHMM identifier46
5.1.2VQ-distortion identifier47
5.1.3實驗結果48
5.2基於碼書調適之語者補償53
5.3使用強健性特徵參數55
第六章結論與展望62
6.1結論62
6.2未來展望64
參考文獻65
附錄A、68
[1] 時行,台灣文月刊,台語文會發行,1999.3,第五期。
[2] 謝國平,"語言學概論",三民書局,第四章,1996年八月。
[3] 鄭良偉,鄭謝淑娟,"台灣福建話的語音結構及標音法",學生書局,第2章,1994年九月。
[4] 羅肇錦,"客語語法",學生書局,第2章。1988年九月。
[5] 謝雲飛,"語音學大綱",學生書局,第6章,1994年十月3刷,
[6] Lin-shan Lee, et al., "Golden Mandarin (I)-A Real-Time Mandarin Speech Dictation Machine for Chinese Language with Large Vocabulary," IEEE Transactions on Speech and Audio Processing, VOL.1, NO.2, APRIL 1993.。
[7] 羅肇錦,"台灣的客家話",臺原出版社,第12章。
[8] L. R. Rabiner and B. H. Juang, "An Introduction to Hidden Markov Models," IEEE ASSP MAGAZINE, JANUARY 1986.
[9] Joseph Picone, "Continuous Speech Recognition Using Hidden Markov Models," IEEE ASSP MAGAZINE, JULY 1990.
[10] 蔡偉和,"不特定語者之中國方言自動辨識",國立交通大學碩士論文,民國八十六年。
[11] Wuei-He Tsai and Wen-Whei Chang, "Chinese Dialect Identification Using An Acoustic-Phontactic Model," European Conference on Speech Communication and Technology, Budapest, Hungary, Sep. 1999.
[12] Yunxin Zhao, "An Acoustic-Phonetic-Based Speaker Adaptation Technique for Improving Speaker-Independent Continuous Speech Recognition," IEEE Transactions on Speech and Audio Processing, vol. 2, no. 3, pp.380-394, JULY 1991.
[13] Xuedong Huang and Kai-Fu Lee, "On Speaker-Independent, Speaker-Dependent, and Speaker-Adaptive Speech Recognition," IEEE Transactions on Speech and Audio Processing, vol. 1, no. 2, pp. 150-157, April 1993.
[14] Tomoko Matsui and Sadaoki Furui, "Comparison of Text-Independent Speaker Recognition Methods Using VQ-Distortion and Discrete/Continuous HMM''s," IEEE Transactions on Speech and Audio Processing, vol. 2, no. 3, JULY 1991.
[15] Mazin G. Rahim et al., "signal Conditioning Techniques for Robust Speech recognition," IEEE Signal Processing Letters, VOL. 3, NO. 4, APRIL 1996.
[16] Rathinavelu Chengalvarayan, "Speaker Adaptation Using Discriminative Linear Regression on Time-Varying Mean Parameters in Trended HMM," IEEE Signal Processing Letters, VOL. 5, NO. 3, MARCH 1998.
[17] Xavier Aubert and Eric Thelen, "Speaker Adaptive Training Applied to Continuous Mixture Density Modeling," Philips Gmbh Forschungs laboratorien Aachen.
[18] Rathinavelu Chengalvarayan, "Speaker Adaptation Using Discriminative Linear Regression on Time-Varying Mean Parameters in Trended HMM," IEEE Signal Processing Letters, VOL. 5, NO. 3, MARCH 1998.
[19] STEVEN F. BOLL, "Supression of Acoustic Noise in Speech Using Spectral Subtraction," IEEE Transactions on Acoustics, Speech, ans Signal Processing, VOL. ASSP-27, NO.2, APRIL 1979.
[20] H. C. Choi and R. W. King, "On the Use of Spectral Transformation for Speaker Adaptation in HMM Based Isolated-Word Speech Recognition," Speech Communication, vol. 17, pp. 131-143, 1995.
[21] Chin-Hui Lee, Chih-Heng Lin, and Biing-Hwang Juang, "A Study on Speaker Adaptation of the Parameters of Continuous Density Hidden Markov Models," IEEE Transactions on Speech and Audio Processing, vol. 39, no. 4, pp. 806-814, April 1991.
[22] C. J. Leggetter and P. C. Woodland, "Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models," Computer Speech and Language, vol. 9, pp. 171-185, 1995.
[23] John R. Deller, John G. Proakis, and John H. L. Hansen, "Disrete-time processing of speech signals," pp. 374-378, chapter7.
[24] L. R. Rabiner et al.,"On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word Recognition", the BELL system technical Journal, VOL. 62, NO. 4, April, 1983.
[25] Lawrence Rabiner, and Biing-Hwang Juang, "FUNDAMENTALS OF SPEECH RECOGNITION," Chapter3, Chapter4.
[26] Richard J. Mammone, Xiaoyu Zhang and Ravip. Ramachandran, "Robust Speaker Recognition," IEEE Signal Processing Magazine, pp. 58-71, September 1996.
[27] Richard A. Altes, "The Fourier-Mellin transform and mammalian hearing," J. Acoust. Soc. Am., Vol. 63, No. 1, January 1978.
[28] PHILIP E. ZWICKE, "A New Implementation of the Mellin and its Application to Radar Classification of Ships," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-5, No.2, MARCH 1983.
[29] Jingdong Chen, Bo Xu and Taiyi Huang, "A Novel Robust Feature of Speech Signal Based on the Mellin Transform for Speaker-Independent Speech Recognition," ICASSP 98.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔