Current projects:
  1. Multimodal Chinese language model development for text and speech
    (Institute of Information Science, Academia Sinica, 2025/1/1-2026/12/31) Co-PI

  2. Voice Conversion with Applications to Electrolaryngeal Speech Processing
    (National Science and Technology Council, 2025/8/1-2028/7/31) PI

  3. An Interactive Language Learning AI Platform for the Taiwanese Context: Multimodal Technology Development with a Focus on Educational Applications (1/2)
    (National Science and Technology Council, 2026/5/1-2026/10/31) PI


Past projects:
  1. Research and Development of Mandarin-Taiwanese Code-Mixing Speech Recognition System
    (National Science and Technology Council, 2023/8/1-2026/7/31) PI

  2. Data to Chatbot
    (Institute of Information Science, Academia Sinica, 2022/1/1-2024/12/31) Co-PI

  3. Automatic Speech Recognition Based on Discriminative Autoencoder
    (Ministry of Science and Technology, 2021/8/1-2024/7/31) PI

  4. Listen Watch and Read: Multimodal Information Authenticity Detection and Source Tracking
    (Ministry of Science and Technology, 2020/8/1-2023/7/31) PI

  5. Conversational Open Domain Document-based Natural Speech Q&A (COSQA)
    (Institute of Information Science, Academia Sinica, 2020/1/1-2020/12/31) Co-PI
    (Institute of Information Science, Academia Sinica, 2021/1/1-2022/12/31) PI

  6. Merging Heterogeneous Deep Models and Learning Retrieval Features
    (Ministry of Science and Technology, 2018/1/1-2021/12/31) Co-PI

  7. Deep Intelligence Based Spoken Language Processing
    (Ministry of Science and Technology, 2018/1/1-2021/12/31) Co-PI

  8. Voice Conversion and its Applications
    (Ministry of Science and Technology, 2018/8/1-2021/7/31) PI

  9. Representation Learning and Its Applications in Speech and Music Processing
    (Ministry of Science and Technology, 2016/8/1-2019/7/31)

  10. Enhancing Intelligent Sensing Capability of Home Robots via Deep Learning
    (Institute of Information Science, Academia Sinica, 2017/1/1-2018/12/31)

  11. Video/Audio Enhancement and Recognition by Deep Learning
    (Institute of Information Science, Academia Sinica, 2015/1/1-2016/12/31)

  12. Context-Aware and Personalized Music Recommendation
    (Ministry of Science and Technology, 2013/8/1-2016/7/31)

  13. The Sustainable Management of Taiwan Digital Archives
    (Ministry of Science and Technology, 2013/2/1-2016/1/31)

  14. Social Tagging for Music Information Retrieval and Applications
    (National Science Council, 2012/8/1-2015/7/31)

  15. Taiwan e-Learning and Digital Archives Program
    (National Science Council, 2007/12/1-2012/12/31)

  16. Research on Multilingual Automatic Speech Recognition using Articulatory Knowledge Sources
    (National Science Council, 2010/8/1-2013/7/31)

  17. Next generation Automatic Speech Recognition (Phase II) - Subproject 2: Automatic Labeling and Validation of Speech Databases
    (National Science Council, 2008/8/1-2011/7/31, Phase I: 2005/8/1-2008/7/31)
    NGASR2004, NGASR2005, WWNGASR2005

  18. Speaker Diarization in Audio Recordings
    (National Science Council, 2007/8/1-2010/7/31)

  19. New Generation Speech Science and Technologies - from Fundamentals to Applications
    (National Science Council, 2005/6/1-2008/10/31)

  20. Next generation Automatic Speech Recognition - Subproject 5: Development of Linguistic and Phonological Knowledgebase for Next-Generation Automatic Speech Recognition
    (National Science Council, 2005/8/1-2008/7/31)

  21. Integration of Speech and Speaker Recognition for Biometric Person Authentication
    (National Science Council, 2004/8/1-2007/7/31)

  22. New Directions for Mandarin Speech Synthesis: From Prosodic Organization to More Nature Output
    (Academia Sinica, 2003/1/1-2005/12/31)

  23. Chinese Multimedia Information Extraction
    (Academia Sinica, 2002/1/1-2004/12/31)

  24. Spontaneous Mandarin Speech: Corpus and Processing (1/3, 2/3, 3/3)
    (National Science Council, 2001/8/1/-2004/7/31)
    MATBN - the Mandarin Chinese broadcast news corpus

  25. A Study on Database Technology for Electronic Audio/Video Digital Archive
    (National Science Council, 2003/3/1-2004/7/31)

  26. Speech Information Retrieval in a Wireless Communication Environment (1/3, 2/3, 3/3)
    (National Science Council, 2000/8/1-2003/7/31)

  27. Development of Audio Processing Techniques and A Retrieval System for Video
    (National Science Council, 2001/5/1-2002/4/30)

  28. Mandarin-English Information
    (An NSF Workshop at The Johns Hopkins University, 2000/7/1-2000/8/31)
    abstract report

  29. Research on Automatic Recognition of Mandarin Broadcast News Speech
    (National Science Council, 1999/8/1-2000/7/31)

  30. Research on Mandarin Speech Database Retrieval Using Quasi-Natural-Language Queries
    (National Science Council, 1998/8/1-1999/7/31)

  31. Research on Mandarin Speech Database Retrieval
    (National Science Council, 1997/8/1-1998/7/31)