Honor

  • 2015.10 - OCOCOSDA 2015 ITN Best Paper Award: Chen-Yu Chiang, "A Study on Adaptation of Speaking Rate-Dependent Hierarchical Prosodic Model for Chinese Dialect TTS," in Proc. OCOCOSDA 2015, Shanghai, China, Oct. 2015.
  • 2015.06 - Undergraduate course: Practice Project - An Automatic Grade Input System via Voice, Students: 賴建宏、葉瀚允, First Place Award, at Practice Project Competition, Dept. of Communication Engineering, National Taipei University
  • 2015.06 - Undergraduate course: Practice Project - 英文逐字對照發音語言學習系統開發, Students: 潘祈睿、吳依庭、黃筱真、楊忠翰, Honorable Mention at Practice Project Competition, Dept. of Communication Engineering, National Taipei University
  • 2014.09 - OCOCOSDA 2014 ITN Best Paper Award: Yu-Ping Hung, Han-Yun Yeh, I-Bin Liao, Chen-Ming Pan, and Chen-Yu Chiang, "An investigation on linguistic features for Mandarin prosody generation," in Proc. OCOCOSDA 2014, Phuket, Thailand, Sept. 2014.

Biography

Chen-Yu Chiang was born in Taipei, Taiwan, in 1980. He received the B.S., M.S., Ph.D. degrees in communication engineering from National Chiao Tung University (NCTU), Hsinchu, Taiwan, in 2002, 2004, and 2009, respectively. In 2009, he was a Postdoctoral Fellow at the Department of Electrical Engineering, NCTU, where he primarily worked on prosody modeling for automatic speech recognition and text-to-speech system, under the guidance of Prof. Sin-Horng Chen. In 2012, he was a Visiting Scholar at the Center for Signal and Image Processing (CSIP), Georgia Institute of Technology, Atlanta. Currently he is the director of the Speech and Multimedia Signal Processing Lab and an assistant professor at the Department of Communication Engineering, National Taipei University. His main research interests are in speech processing, in particular prosody modeling, automatic speech recognition and text-to-speech systems.

Educations

  • Doctor of Engineering in Communication Engineering, National Chiao Tung University, 2009
  • Master of Engineering in Communication Engineering, National Chiao Tung University, 2004
  • Bachelor of Engineering in Communication Engineering, National Chiao Tung University, 2002

Specialty

  1. Digital Speech Processing
  2. Natural Language Processing
  3. Pattern Recognition
  4. Audio Signal Processing

Publications

Journal Papers

  1. Sin-Horng Chen, Chiao-Hua Hsieh, Chen-Yu Chiang, Hsi-Chun Hsiao, Yih-Ru Wang, Yuan-Fu Liao and Hsiu-Min Yu, “Modeling of Speaking Rate Influences on Mandarin Speech Prosody and Its Application to Speaking Rate-controlled TTS,” , IEEE Trans. on Audio, Speech and Language Processing, vol.22, no. 7, pp.1158-1171, July. 2014.
  2. Sin-Horng Chen, Jyh-Her Yang, Chen-Yu Chiang, Ming-Chieh Liu and Yih-Ru Wang, "A New Prosody-Assisted Mandarin ASR System", IEEE Trans. on Audio, Speech and Language Processing, vol.20, no.6, pp.1669,1684, Aug. 2012.
  3. Chen-Yu Chiang, Yih-Ru Wang, Qi-Quan Huang, Hsiu-Min Yu, and Sin-Horng Chen, "Variable Speech Rate Mandarin Chinese Text-to-Speech System," accepted for publication in the International Journal of Computational Linguistics and Chinese Language Processing. (in Chinese)
  4. Chen-Yu Chiang, Sin-Horng Chen, Hsiu-Min and Yu, Yih-Ru Wang, “Unsupervised Joint Prosody Labeling and Modeling for Mandarin Speech,” J. Acoust. Soc. Am., vol. 125, No. 2, pp. 1164-1183, Feb, 2009.
  5. International Conference/Symposium/Workshop Papers:

  1. Chen-Yu Chiang, “A Study on Adaptation of Speaking Rate-Dependent Hierarchical Prosodic Model for Chinese Dialect TTS,” in Proc. OCOCOSDA 2015, Shanghai, China, Oct. 2015. (Best Paper Award)
  2. Fu-Ja Kung, Pa-Hwa Lee, Yih-Ru Wang, Chen-Yu Chiang, and Sin-Horng Chen, “On Finding Word-Level Break-Type Formation Rules for Mandarin Read Speech,” in Proc. OCOCOSDA 2015, Shanghai, China, Oct. 2015.
  3. Yu-Ping Hung, Han-Yun Yeh, I-Bin Liao, Chen-Ming Pan, and Chen-Yu Chiang, “An investigation on linguistic features for Mandarin prosody generation,” in Proc. OCOCOSDA 2014, Phuket, Thailand, Sept. 2014. (Best Paper Award)
  4. Chung-Yao Tsai, Chin-Kuan Kuo, Yih-Ru Wang, Sin-Horng Chen, I-Bin Liao, and Chen-Yu Chiang, "Hierarchical prosody modeling of English speech and its application to TTS," in Proc. OCOCOSDA 2014, Phuket, Thailand, Sept. 2014.
  5. Guan-Ting Liou, Wen-Li Zhuang,Chen-Yu Chiang, Wern-Jun Wang, Pao-Ching Chen, Yih-Ru Wang, Sin-Horn Chen, “A Study on Polyphone Disambiguation and Tone 3 Sandhi Labeling for Traditional Chinese,” 17th International Conference Oriental COCOSDA, Phuket, Thailand, Sept. 2014
  6. Po-Chun Wang, I-Bin Liao,Chen-Yu Chiang, Yih-Ru Wang, and Sin-Horng Chen, “Speaker adaptation of speaking rate-dependent hierarchical prosodic model for Mandarin TTS,” in Proc. ISCSLP 2014, Singapore, Sept. 2014, pp. 511-515.
  7. Chen-Yu Chiang, Yu-Ping Hung, Sin-Horng Chen, and Yih-Ru Wang, “A New Model-Based Prosody Coder for Mandarin Speech,” in Proc. of IIHMSP 2013, Beijing, China, Oct. 2013, pp. 60-63.
  8. Chen-Yu Chiang, Sabato Marco Siniscalchi, Sin-Horng Chen, and Chin-Hui Lee, “Knowledge integration for improving performance in LVCSR,” in Proc. Interspeech 2013, Lyon, France, Aug. 2013, pp. 1786-1790.
  9. Chiao-Hua Hsieh, Yih-Ru Wang, Chen-Yu Chiang, and Sin-Horng Chen, "A speaking rate-controlled Mandarin TTS system," Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pp.6900,6904, 26-31 May 2013
  10. Chen-Yu Chiang, Siniscalchi, S.M., Yih-Ru Wang, Sin-Horng Chen, and Chin-Hui Lee, "A study on cross-language knowledge integration in Mandarin LVCSR," Chinese Spoken Language Processing (ISCSLP), 2012 8th International Symposium on, pp.315,319, 5-8 Dec. 2012
  11. Chao-Yu Lin, Kai-Tai Song, Yi-Wen Chen, Shuo-Cheng Chien, Sin-Horng Chen, Chen-Yu Chiang, Jyh-Her Yang, Yi-Chiao Wu, and Tzu-Jui Liu, "User identification design by fusion of face recognition and speaker recognition," Control, Automation and Systems (ICCAS), 2012 12th International Conference on , pp.1480,1485, 17-21 Oct. 2012.
  12. Hsiu-Min Yu, Chen-Yu Chiang, Yih-Ru Wang and Sin-Horng Chen, "Effects of prosodic position on the production of Si-Xien Hakka tones at phrase level (Abstract)." to be presented at Acoustics 2012, Hong Kong May 2012.
  13. Tzu-Hsuan Chiu, Chen-Yu Chiang, Yuan-Fu Liao, Jyh-Her Yang, Yih-Ru Wang and Sin-Horng Chen, “Prosody-dependent Acoustic Modeling for Mandarin Speech Recognition,” to be appeared in Speech Prosody 2012, Shanghai, China, May 2012.
  14. Chen-Yu Chiang, Yih-Ru Wang and Sin-Horn Cheng, “Punctuation Generation Inspired Linguistic Features for Mandarin Prosodic Boundary Prediction,” to be appeared in Proc. ICASSP 2012, Kyoto, Japan, May 2012.
  15. Hsiu-Min Yu, Hsiu-Hsueh Liu, Jyh-Her Yang, Chen-Yu Chiang, Sin-Horng Chen, “Tonal Contrast and Pitch Range in L2 Taiwan Min Produced by Native Si-Xien Hakka Speakers,” presented in 12th International Conference on Min Languages, Institute of Linguistics, Academia Sinica, Taiwan, Nov. 2011.
  16. Chen-Yu Chiang, Jyh-Her Yang, Ming-Chieh Liu, Yih-Ru Wang, Yuan-Fu Liao and Sin-Horng Chen, “A New Model-based Mandarin-speech Coding System,” in Proc. Interspeech 2011, Florence, Italy, Aug. 2011, pp 2561-2564.
  17. Jyh-Her Yang, Ming-Chieh Liu, Hao-Hsiang Chang, Chen-Yu Chiang, Yih-Ru Wang, and Sin-Horng Chen, “Enriching mandarin speech recognition by incorporating a hierarchical prosody model,” in Proc. ICASSP 2011, Praque, Czech, May, 2011, pp 5052-5055.
  18. Tsai-Lu Tsai, Chen-Yu Chiang, Hsiu-Min Yu, Lieh-Shih Lo, Yih-Ru Wang and Sin-Horng Chen , "A Study on Hakka and Mixed Hakka-Mandarin Speech Recognition," in Proc. ISCSLP 2010, Tainan, ROC., Nov. 2010, pp. 199-202.
  19. Yi-Ling Tsai, Hsiu-Min Yu, Yih-Ru Wang, Chen-Yu Chiang, Lieh-Shih Lo, Sin-Horng Chen, “An HMM-based Hakka Text-to-Speech System,” in Proc. O-COCOSDA 2010, Nepal, Oct. 2010.
  20. Chen-Yu Chiang, Sin-Horng Chen, and Yih-Ru Wang , "Unsupervised prosody labeling for constructing Mandarin TTS" , in Proc. 7th ISCA Speech Synthesis Workshop (SWW7), Kyoto, Japan, Sept. 2010, pp 264-269.
  21. Yu-Lun Chou, Chen-Yu Chiang, Yih-Ru Wang, Hsiu-Min Yu, Sin-Horng Chen, “Prosody Labeling and Modeling for Mandarin Spontaneous Speech,” in Proc. Speech Prosody 2010, Chicago, USA, May 2010.
  22. Hsin-Te Hwang, Chen-Yu Chiang, Po-Yi Sung, and Sin-Horng Chen, “A Novel Model-based Pitch Conversion Method for Mandarin Speech,” in Proc. Interspeech 2009, Brighton, UK, Sept. 2009, pp. 2643-2645.
  23. Chen-Yu Chiang, Sin-Horng Chen and Yih-Ru Wang, “Advanced Unsupervised Joint Prosody Labeling and Modeling for Mandarin Speech and Its Application to Prosody Generation for TTS,” in Proc. Interspeech 2009, Brighton, UK, Sept. 2009, pp. 504-507.
  24. Chen-Yu Chiang, Cheng-Chang Tang, Hsiu-Min Yu, Yih-Ru Wang and Sin-Horng Chen, “An Investigation on the Mandarin Prosody of a Parallel Multi-Speaking Rate Speech Corpus,” in Proc. Oriental COCOSDA 2009, Beijing, China, pp.148-153.
  25. Hung-Kuang Shih, Chen-Yu Chiang, Yih-Ru Wang and Sin-Horng Chen, "Prosodic Modeling For Isolated Mandarin Words And Its Application," in Proc. ICSCLP 2008, Kunming, China, Dec. 2008, pp. 1-4.
  26. Chen-Yu Chiang, Hsiu-Min Yu, Yih-Ru Wang, Sin-Horng Chen, "Exploration of High-level Prosodic Patterns for Continuous Mandarin Speech," in Proc. ICASSP 2008, Las Vegas, USA, April 2008, pp. 4381-4384.
  27. Chen-Yu Chiang, Hsiu-Min. Yu, Yih-Ru Wang, Sin-Horng Chen, "An Automatic Prosody Labeling Method for Mandarin Speech," in Proc. Interspeech 2007, Antwerp, Belgium, Sept. 2007, pp. 494-497.
  28. Chen-Yu Chiang, Xiao-Dong Wang, Yuan-Fu Liao, Yih-Ru Wang, Sin-Horng Chen, Keikichi Hirose, "Latent Prosody Modeling of Continuous Mandarin Speech," in Proc. ICASSP 2007, Honolulu, USA, Apr. 2007, pp. 625-628.
  29. Chen-Yu Chiang, Yih-Ru Wang and Sin-Horng Chen, "On the Inter-syllable Coarticulation Effect of Pitch Modeling for Mandarin Speech," in Proc. Interspeech 2005, Lisboa, Portugal, Sept. 2005, pp. 3269-3272.
  30. Yih-Ru Wang and Chen-Yu Chiang, "A New Common Component GMM-based Speaker Recognition Method", in Proc. ICASSP 2005, Philadelphia, USA, Apr. 2005, pp. 645-648.

Domestic Conference Papers

  1. Qi-Quan Huang, Chen-Yu Chiang, Yih-Ru Wang, Hsiu-Min Yu and Sin-Horng Chen, “Variable Speech Rate Mandarin Chinese Text-to-Speech System,” Proc. of ROCLING 2010, Puli, Nantou, ROC. pp. 222-235, 2010. (in Chinese)
  2. Chi-Feng Chen, Chen-Yu Chiang, Yih-Ru Wang, and Sin-Horng Chen, "A Study on Prosodic Modeling for Isolated Mandarin Words," Proc. of ROCLING 2007, Taipei, ROC. pp. 273-286, 2007. (in Chinese)

Survey Article

  1. 洪宇平、江振宇, “中文韻律產生使用之語言參數研究,” Association for Computational Linguistics and Chinese Language Processing (ACLCLP) Newsletter, Vol.25 No.1, pp. 7-18, June, 2014. (in Chinese)
  2. Chen-Yu Chiang, Hsi-Chun Hsiao, Hsiu-Min Yu and Yuan-Fu Liao , "Introduction to Speech Prosody," Association for Computational Linguistics and Chinese Language Processing (ACLCLP) Newsletter, Vol.18 No.2, pp. 5-19, June, 2007. (in Chinese)

Technical Report

  1. Xiao-Dong Wang, Jin-Song Zhang, Keikichi Hirose, Nobuaki Minematsu, Chen-Yu Chiang, Yih-Ru Wang and Yuan-Fu Liao, "Tone Recognition of Continuous Mandarin Speech Based on Tone Nucleus Model and MLP Nucleus Network,", IEICE technical report. Speech, Nagoya, Japan, Vol. 106, No. 443, pp. 107-112, SP2006-103, Dec, 2006.

Patents

  1. Sin-Horng Chen, Yih-Ru Wang, Chen-Yu Chiang, and Chiao-Hua Hsieh, “Speaking-Rate Controlled Prosodic-Information Generating Device and Speaking-Rate Dependent Hierarchical Prosodic Module,” U.S. and Taiwan, patent pending.
  2. Sin-Horng Chen, Yih-Ru Wang, Chen-Yu Chiang, and Chiao-Hua Hsieh, " Streaming Encoder, Prosody Information Encoding Device, Prosody-Analyzing Device, and Device and Method for Speech-Synthesizing, " U.S. and Taiwan, patent pending.
  3. Kai-Tai Song, Shuo-Cheng Chien, Chao-Yu Lin, Yi-Wen Chen, Sin-Horn Chen, Chen-Yu Chiang, Yi-Chiao Wu, "Identity Recognition by Fusion of Face Recognition and Speaker Recognition," U.S. and Taiwan, patent pending.
  4. Jyh-Her Yang, Chen-Yu Chiang, Ming-Chieh Liu, Yih-Ru Wang, Yuan-Fu Liao, Sin-Horng Chen, "Chinese speech recognition device and speech recognition method thereof," U.S. and Taiwan, patent pending.

Dissertation and Thesis

  • Ph.D. Dissertation: "Unsupervised Joint Prosody Labeling and Modeling for Mandarin Speech," National Chiao Tung University, 2009. (Advisors: Prof. Sin-Horng Chen and Prof. Yih-Ru Wang)
  • Master Thesis: "An Improvement on Chinese Parser," National Chiao Tung University, 2004. (Advisor: Prof. Sin-Horng Chen)

Employments

  • Assistant Professor, Department of Communication Engineering, National Taipei Univerity, Aug. 2012 - now
  • Postdoctoral Research Fellow, Department of Electrical Engineering, College of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan, Apr. 2009 - July 2012

Research

Interests

  1. Speech Recognition -prosody-assisted automatic speech recognition, hierarchical language modeling, search algorithm,prosody-dependent acoustic modeling, Chinese dialect (Min-Nan and Hakka) speech recognition
  2. Audio Signal Processing - singing voice synthesis, music retrieval, chord recognition
  3. Prosody Modeling -prosody hierarchy construction,prosody generation,prosody analysis of native/non-native speakers, spontaneous speechprosody modeling, speaking rate modeling
  4. Text-to-Speech System - text analysis,prosody generation, speech synthesizer, variable speaking rate TTS
  5. Natural Language Processing - word identification,part of speech tagging,phrase identification,punctuation generation, syntax analysis.
  6. Spoken Dialog System - dialog management, system integration, design of user interface

Experience

2014.1 –present

Position: Primary Investigator

Project: Hybrid unit-selection speech synthesis

Grant: TL-102-8202, Chunghwa Telecom Laboratories, Taiwan

Content:

  1. Construction of a high-quality text-to-speech system
  2. A study on a fully-automatic text analysis
  3. Prosody modeling for Mandarin speech
  4. A study on hybrid speech synthesis method

2013.8 –present

Position: Primary Investigator

Project: Prosody Modeling for English and its Applications

Grant: NSC-102-2221-E-305-005-MY3, Ministry of Science and Technology

Content:

  1. Prosody modeling for isolated English word
  2. Prosody modeling for continuous English
  3. Cross-linguistic (Mandarin and English)prosody modeling
  4. Application to speech recognition and text-to-speech
  5. Application to computer-aided language learning system

2013.4 – 2014.1

Position: Multiple Primary Investigator

Project: A Study on Audio Event Detection in a Parking Lot Surveillance

Grant: Orbit Tech. Inc.

Content:

  1. Construction of a real-time audio event detector

2013.1 – 2013.12

Position: Joint Primary Investigator

Project: Research on Timbre Parameterization and Matching for Voices of Residents of Taiwan

Grant: B101111301, Investigation Bureau, Ministry of Justice, Taiwan

Content:

  1. Construction of a text-dependent speaker verification system

2012.9 - 2013.7

Position: Primary Investigator

Project: Prosody Modeling for Computer-Assisted English Learning System

Grant: NSC-101-2218-E-305-002, National Science Council, Taiwan

Content:

  1. Prosody modeling for American English
  2. Knowledge (prosodic structure and articulatory information) integration for American English automatic speech recognition
  3. Cross-language knowledge integration (Mandarin and American English) for Mandarin large vocabulary speech recognition

2012.1 - 2012.5

Position: Visiting scholar, the Center for Signal and Image Processing (CSIP), School of Electrical and Computer Engineering (ECE), Georgia Institute of Technology, Atlanta, with Prof. Chin-Hui Lee.

Grant: the Top University and Elite Research Center Development Plan of Ministry of Education, Taiwan (MoE ATU Plan)

Content:

  1. Prosody-based knowledge integration for automatic speech recognition (cooperate with Prof. Sabato Marco Siniscalchi, Department of Telematics, Kore University of Enna, Enna, Italy)
  2. Construction American English Text-to-Speech System.

2011.8 – 2012.6

Position: Project member

Project: Cross-genre and cross-linguisticprosody modeling of discourse and information structure, NSC-100-2221-E-001-019-MY3 (PI: Dr. Chiu-Yu Tseng, Institute of Linguistics, Academia Sinica)

Content:

  1. Computational comparison study on speechprosody of native and non-native English speakers.

2011.4 -present

Position: Project member

Project: Advanced Study on Prosody Modeling for Spoken Mandarin Speech (supported by National Chiao Tung University, Taiwan) (PI: Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan)

Content:

  1. Collaborating with Prof. Ho-Hsien Pan, Department of Foreign Languages and Literatures, National Chiao Tung University, Taiwan.
  2. Collecting Taiwan Min speech corpora
  3. Automatic tone labeling for Taiwan Min speech corpora.

2011.5 – 2012.6

Position: Project member

Project: Design and development of the Chinese DAISY talking bookplayer, NSC100-2218-E011-014 (PI: Prof. Yuan-Hsiang Lin, Department of Electronic Engineering, National Taiwan University of Science and Technology)

Content:

  1. Providing the source code of the NCTU PC-based Mandarin text-to-speech system (http://140.113.144.71/download/libmtts-0.0.rar)
  2. Providing short courses of text-to-speech technology
  3. Assisting inporting the source code to the linux and the androidplatforms

2010.8 – 2012.6

Position: Project member

Project: Sophisticated Multi-Level Prosody Hierarchy Construction for Mandarin Speech and its Application, NSC-99-2221-E-009-009-MY li (PI: Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan)

Content:

  1. Speechprosody coding
  2. Prosody generation modeling
  3. Prosody-dependent acoustic modeling
  4. Continuous speaking rate modeling

2009.12 - 2011.11

Position: Project member

Project: A industry-university collaborationproject (Compal Communications, Inc, and National Chiao Tung University) - Speechprosody module development for customizedproducts (I and II), NSC-99-2622-E-009-005-CC2 (PI: Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan) - subproject of the mainproject - A Robust Speech and Visual Interface for Intelligent Robots (I and II) (PI: Prof. Jwu-Sheng Hu, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan).

Content:

  1. Project management
  2. Construction and maintenance of the software versioning system (Subversion, SVN) for theproject
  3. Assisting in constructing a PC-based real-time speaker identification/verification system, a PC-based real-timeprosody-assisted keyword spotting system, and a PC-based Mandarin text-to-speech system.
  4. Assisting in the integration of the face recognizer (image) and the speaker recognizer (speech).
  5. Assisting in technology transfers: a PC-based real-time speaker identification/verification system and a PC-based real-timeprosody-assisted keyword spotting system

2009.8 – 2012.6

Position: Postdoctoral research fellow, Department of Electrical Engineering, National Chiao Tung University, Taiwan.

Project: Huge-Vocabulary Mandarin Speech Recognition, NSC-98-2221-E-009-075-MY li (PI: Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan)

Content:

  1. Prosody modeling for a very large vocabulary automatic speech recognition system
  2. Assisting in constructing a weighted finite state transducer (WFST)-based large vocabulary continuous speech recognizer (LVCSR).

2009.4 - 2009.7

Position: Postdoctoral research fellow, Department of Electrical Engineering, National Chiao Tung University, Taiwan.

Project: A Study on Corpus-Based Text-To-Speech and Speech Recognition for Hakka Language (III), NSC- 96-2221-E-009-030-MY li (PI: Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan)

Content:

  1. Hakka language model construction
  2. Hakka text-to-speech system construction
  3. Hakka-Mandarin mixed language speech recognition
  4. Hakka lexicon collection.

2006.8 - 2009.7

Position: Research Assistant, Institute of Communication Engineering, National Chiao Tung University, Taiwan.

Project: Prosody Hierarchy Construction for Mandarin Speech and Its Application to Speech Recognition (I ~ III), NSC- 95-2221-E-009-057-MY li (PI: Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan)

Content:

  1. Unsupervised jointprosody labeling and modeling for continuous Mandarin read speech
  2. Prosody conversion
  3. Prosody modeling for various speech rates, various speakers and spontaneous speech.

2006.6.25-2006.9.1

Position: Visiting Researcher, Hirose & Minematsu Laboratory, The University of Tokyo, Japan, with Prof. Keikichi Hirose

Grant: NSC of Taiwan,project - New Generation Speech Science and Technologies-from Fundamentals to Applications

Content:

  1. Prosody modeling and Chinese Tone Recognition - two jointpublications:
  2. Chen-Yu Chiang, Xiao-Dong Wang, Yuan-Fu Liao, Yih-Ru Wang, Sin-Horng Chen, Keikichi Hirose, "Latent Prosody Modeling of Continuous Mandarin Speech," in Proc. ICASSP 2007, Honolulu, USA, Apr. 2007,p 625-62 li li Xiao-Dong Wang, Jin-Song Zhang, Keikichi Hirose, Nobuaki Minematsu, Chen-Yu Chiang, Yih-Ru Wang and Yuan-Fu Liao, "Tone Recognition of Continuous Mandarin Speech Based on Tone Nucleus Model and MLP Nucleus Network,", IEICE technical report. Speech, Nagoya, Japan, Vol. 106, No. 443,p 107-112, SP2006-103, Dec, 200 li

2005 - 2006

Position: Research Assistant, Institute of Communication Engineering, National Chiao Tung University, Taiwan.

Project: Further Studies on Acoustic Modeling and Prosodic Modeling for Mandarin Speech (III), NSC- 94-2213-E-009-02 li (PI: Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan)

Content:

  1. Advancedprosody modeling
  2. Mandarin tone recognition

2003.7 - 2005.3

Position: Research Assistant, Institute of Communication Engineering, National Chiao Tung University, Taiwan.

Project: "Human Technology (HT) - Intelligent Transportation Systems (ITS), Subproject (II): Smart Interfacing - Intelligent Dialogue System for ITS Information Access," Program for Promoting Academic Excellence of University Project, Ministry of Education, Taiwan. (PI: Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan)

Content:

  1. Design of the dialog flow and graphic user interface.
  2. Development of an Mandarin Text-to-Speech System (M-TTS).
  3. Integration of in-vehicle speaking assistant system (spoken dialog system for GPS car navigation around HsinChu Science Park and its neighborhood). The system was consisted of M-TTS, an automatic speech recognition engine, a semanticparser, a geographic information system (GIS), a dialog management, a microphone array front-end, a graphic user interface.

Collaboration/Supporting

2010/9 – 2012/6

Development of traditional Chinese Grapheme-phoneme conversion module in EasyAlign - an automatic phonetic alignment tool under Praat, collaborating with professor Jean-Philippe Goldman, Department of Linguistics, University of Geneva, Switzerland. (http://140.113.144.71/download/CHG2P.rar)

2010/7 - 2011/7

NCTU-Microsoft Research Project on Cloud Computing and Communications (PI: Prof. Li-Chun Wang, Department of Electrical Engineering, National Chiao Tung University, Hsinchu, Taiwan)

Providing "Time inquiry by voice service" for the JOIN project.

Scholarly Activities

Membership

  1. Member, Institute of Electrical and Electronics Engineers (IEEE), 2009 -
  2. Member, Acoustical Society of America (ASA), 2011 -
  3. Member, International Speech Communication Association (ISCA), 2009 -
  4. Member, Association for Computational Linguistics and Chinese Language Processing (ACLCLP), 2007

Academic Service

  1. Reviews
    1. IEEE Transaction on Audio, Speech and Language Processing (IEEE T-ASLP), 2011 and 2012
    2. Journal of the Chinese Institute of Engineers (JCIE), 2012
    3. 2012 The IEEE International Symposium on Circuits and Systems (IEEE ISCAS 2012), 2011
    4. The OCOCOSDA2011 conference, 2011
  2. Conference organization
    1. Workshop co-chair, Speech Signal Processing Workshop 2015, Taipei, Taiwan, Mar. 27, 2015, http://sws2015.22web.org/
    2. Workshop chair, Speech Signal Processing Workshop 2014, New Taipei City, Taiwan, Aug. 1, 2014, http://sws2014.cychiang.tw/
    3. Conference organizer, the Oriental COCOSDA 2011 conference, Hsinchu, Taiwan, Oct. 26-28, 2011.
    4. Staff, the 3-th International Symposium on Chinese Spoken Language Processing (ISCSLP 2002), Taipei, Taiwan, Aug. 23-24, 2002

Presentations

  1. "Unsupervised Joint Prosody Labeling and Modeling for Mandarin Speech," National Symposium on Telecommunications, Taipei, Taiwan, Nov. 2007
  2. "Latent Prosody Models of Continuous Mandarin Speech," NeGSST 2006 Winter Seminar, National Chiao Tung University, Hsinchu, Taiwan, Feb. 2007
  3. "Mandarin Text-to-speech System," NeGSST 2006 Winter Seminar, National Chiao Tung University, Hsinchu, Taiwan, Jan. 2006.

Invited talks

  1. “漢語韻律模式及其應用”, Speech Signal Processing Workshop 2013, https://sites.google.com/site/2013speechprse/home/seabstract
  2. “Introduction to Spoken Language Processing,” Dept. of Foreign Language, National Chiao Tung University, Hsinchu, Taiwan, Apr. 2011.
  3. “Prosody Hierarchy Construction for Mandarin Speech and Its Application to Speech Recognition,” NGASR, Academia Sinica, Taipei, Taiwan, Aug. 2010.
  4. “Unsupervised Joint Prosody Labeling and Modeling for Mandarin Speech,” Academia Sinica, Taipei, Taiwan, Sept. 2009.

Conference/Symposium/Workshop Attended

  1. OCOCOSDA 2015, Shanghai, China, Oct. 28-30, 2015
  2. OCOCOSDA 2014, Phuket, Thailand, Sept. 10-12, 2014
  3. International Speech Communication Association (ISCA) Interspeech 2013, Lyon, France, Aug. 25-29, 2013.
  4. IEEE ICASSP 2013, Vancouver, Canada, May. 26-31, 2013.
  5. Oriental COCOSDA international conference 2011, Hsinchu, Taiwan, Oct. 26-28, 2011.
  6. International Speech Communication Association (ISCA) Interspeech 2011, Florence, Italy, Aug. 28-Sept. 31, 2011.
  7. The 7-th International Symposium on Chinese Spoken Language Processing (ISCSLP 2010), Tainan, Taiwan, Nov. 29-Dec. 3, 2010
  8. The 7th ISCA Speech Synthesis Workshop (SWW7), Kyoto, Japan, Sept. 22-24, 2010.
  9. The 22nd Conference on Computational Linguistics and Speech Processing (ROCLING 2010), Puli, Nantou, Taiwan, Sept. 1-2, 2010.
  10. The 5-th international conference on speech prosody (ISCA Speech Prosody 2010), Chicago, USA, May 11-14, 2010.
  11. International Speech Communication Association (ISCA) Interspeech 2009, Brighton, UK, Sept. 6-10. 2009.
  12. IEEE ICASSP 2009, Taipei, Taiwan, Apr. 19-24, 2009.
  13. The 20th Conference on Computational Linguistics and Speech Processing (ROCLING 2008), Taipei, Taiwan, Sept. 4-5, 2008.
  14. IEEE ICASSP 2008, Las Vegas, USA, Mar. 30-Apr. 4, 2008.
  15. The 19th Conference on Computational Linguistics and Speech Processing (ROCLING 2007), Taipei, Taiwan, Sept. 6-7, 2008
  16. International Speech Communication Association (ISCA) Interspeech 2007, Antwerp, Belgium, Aug. 27-31, 2007.
  17. IEEE ICASSP 2007, Honolulu, USA, Apr. 15-20, 2007.
  18. The 18th Conference on Computational Linguistics and Speech Processing (ROCLING 2006), Hsinchu, Taiwan, Sept. 6-8, 2006
  19. International Speech Communication Association (ISCA) Interspeech 2005, Lisboa, Portugal, Sept. 4-8. 2005.
  20. IEEE ICASSP 2005, Philadelphia, USA, Mar. 18-23, 2005.
  21. The 4-th International Symposium on Chinese Spoken Language Processing (ISCSLP 2004), Hong Kong, Dec. 16-18, 2004
  22. The 3-th International Symposium on Chinese Spoken Language Processing (ISCSLP 2002), Taipei, Taiwan, Aug. 23-24, 2002

Teaching Experience

2015.8 – 2016.1

  • Undergraduate courses:
    1. Multimedia Signal Processing (course ID: U3229, for Depts. of Communication Engineering, National Taipei University)
  • Graduate school course:
    1. Digital signal processing (course ID: M5631, for Graduate Institute of Communication Engineering, National Taipei University)
    2. Seminar (course ID: M5276, for Graduate Institute of Communication Engineering, National Taipei University)

2015.2 – 2015.6

  • Undergraduate courses:
    1. Physics (course ID: U1182, for Depts. of Communication Engineering, National Taipei University)
    2. Physics Experiments (course ID: U1178, for Depts. of Communication Engineering, National Taipei University)
  • Graduate school course:
    1. Seminar (course ID: M5083, for Graduate Institute of Communication Engineering, National Taipei University)

2014.8 – 2015.1

  • Undergraduate courses:
    1. Multimedia Signal Processing (course ID: U3229, for Depts. of Communication Engineering, National Taipei University)
  • Graduate school course:
    1. Digital signal processing (course ID: M5631, for Graduate Institute of Communication Engineering, National Taipei University)
    2. Seminar (course ID: M5276, for Graduate Institute of Communication Engineering, National Taipei University)

2014.2 – 2014.6

  • Undergraduate courses:
    1. Physics (course ID: U1182, for Depts. of Communication Engineering, National Taipei University)
    2. Physics Experiments (course ID: U1178, for Depts. of Communication Engineering, National Taipei University)
  • Graduate school course:
    1. Special Topics on Digital Signal Processing – Spoken Language Processing (course ID: M5308, for Graduate Institute of Communication Engineering, National Taipei University)

2013.8 – 2014.1

  • Undergraduate courses:
    1. Calculus (course ID: U1330, for Depts. of Communication Engineering and Electrical Engineering, National Taipei University)
    2. Calculus (course ID: U1523, for Dept. of Computer Science and Information Engineering, National Taipei University)
  • Graduate school course:
    1. Digital signal processing (course ID: M5631, for Graduate Institute of Communication Engineering, National Taipei University)

2013.2 – 2013.6

  • Undergraduate courses:
    1. Physics (course ID: U1353, for Depts. of Communication Engineering, National Taipei University)
    2. Physics experiments (course ID: U1085, for Depts. of Communication Engineering, National Taipei University)
  • Graduate school course:
    1. Special Topics on Digital Signal Processing – Spoken Language Processing (course ID: M5291, for Graduate Institute of Communication Engineering, National Taipei University)

2012.8 – 2013.1

  • Undergraduate courses:
    1. Calculus (course ID: U1330, for Depts. of Communication Engineering and Electrical Engineering, National Taipei University)
    2. Calculus (course ID: U1523, for Dept. of Computer Science and Information Engineering, National Taipei University)
  • Graduate school course:
    1. Digital signal processing (course ID: M5631, for Graduate Institute of Communication Engineering, National Taipei University)

2009.9 - 2010.7

  • Assisting in supervising graduate student Tsai-Lu Tsai (蔡財祿)
  • Master thesis: Tsai-Lu Tsai, "A study on Mixed Hakka-Mandarin Chinese Bilingual Speech Recognition," National Chiao Tung University, 2010. (supervisor: Prof. Sin-Horng Wang, Department of Electrical Engineering, National Chiao Tung University, Taiwan)
  • Honor: 第十屆中華民國計算語言學學會碩士論文佳作

2009.7 - 2010.2

  • Teaching Assistant of Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Taiwan.
  • Undergraduate course: Practice Project - An Implementation of Mandarin Singing Voice Synthesis System (中文歌聲合成系統實作), Grant: NSC 98-2815-C-009-022-E
  • Student: 林可涓
  • Honor: 國科會98年度大專學生參與專題研究計畫」研究創作獎

2009.7 - 2010.2

  • Teaching Assistant of Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Taiwan.
  • Undergraduate course: Practice Project - 走音救星–歌聲評分專題
  • Student: 胡祥容、許馥真、胡仲萱、張玲華

2009.2 - 2010.1

  • Teaching Assistant of Prof. Sin-Horng Chen, Department of Electrical Engineering, National Chiao Tung University, Taiwan.
  • Undergraduate course: Practice Project - Chinese Chess Playing by Voice Contrul (語音象棋)
  • Students: 邱子軒、陳韋帆

2008.9 - 2009.7

  • Assisting in supervising graduate student Yu-Lun Chou (周裕倫)
  • Master thesis: Yu-Lun Chou, "Joint Prosody Labeling and Modeling for Mandarin Spontaneous Speech" National Chiao Tung University, 2009. (supervisor: Prof. Yih-Ru Wang, Institute of Communication Engineering, National Chiao Tung University, Taiwan)
  • Honor: 第九屆中華民國計算語言學學會碩士論文佳作

2008.2 - 2008.6

  • Teaching Assistant of Prof. Yih-Ru Wang, Institute of Communication Engineering, National Chiao Tung University, Taiwan.
  • Industrial Tech R&D Program on Communication Engineering: Digital Speech Processing and its Application to Speech Coding

2006.7 - 2007.2

  • Teaching Assistant of Prof. Sin-Horng Chen, Department of Communication Engineering, National Chiao Tung University, Taiwan.
  • Undergraduate course: Practice Project - A preliminary study on prosodic modeling for emotional speech synthesis(情緒語音合成之韻律模式初探) Grant: NSC 95-2815-C-009-014-E
  • Student: Hung-Kuang Shih (施宏廣)
  • Honor: 交通大學電信系2007年第七屆大學部專題競賽第二名

2005 - 2007

  • Teaching Assistant of Prof. Yih-Ru Wang, Institute of Communication Engineering, National Chiao Tung University, Taiwan.
  • Graduate course: Digital Speech Processing

2004.2 - 2005.1

  • Teaching Assistant of Prof. Sin-Horng Chen, Institute of Communication Engineering, National Chiao Tung University, Taiwan.
  • Undergraduate course: Practice Project - Spoken dialog system for GPS car navigation
  • Student: Wei-Song Huang (黃為崧)

Laboratory

Speech and Multimedia Signal Processing Lab

Established in 2012, the Speech and Multimedia Signal Processing Laboratory (SMPL) elaborates new and practical technologies for speech processing and multimedia signal processing, provides researchers/students substantial trainings of core algorithms for speech recognition, text-to-speech system, audio event detection, text processing, etc. Research topics in SMPL include but are not limited to: speech recognition, text-to-speech, speech coding, voice conversion, spoken language systems, computer-aided language learning system, audio and acoustic signal processing, music signal processing, natural language processing, machine learning for signal processing, etc.

NTPU TTS Demo

Click me to link the deme page