Prof. Yuan-Fu Liao
Biosketch
Yuan-Fu Liao received B.S., M.S., and Ph.D. degrees from the Department of Communication Engineering, National Chiao Tung University (NCTU), Hsinchu, Taiwan, in 1991, 1993, and 1998, respectively. From January 1999 to June 1999, he was a Postdoctoral Researcher at the Department of Communication Engineering, NCTU. From September 1999 to February 2002, he served as a Research Engineer at Philips Research East Asia, Taiwan. From February 2002 to July 2022, he was affiliated with the Department of Electronic Engineering, National Taipei University of Technology (NTUT), Taipei, Taiwan.
Since August 2022, he has been affiliated with the Institute of Artificial Intelligence Innovation at the Industry Academia Innovation School, National Yang Ming Chiao Tung University (NYCU), HsinChu, Taiwan. He currently holds a position as a full Professor and is jointly appointed by the College of Electrical and Computer Engineering at NYCU.
His major research interests include Speech Signal Processing (speech, speaker, language, and emotion recognition; speech synthesis), Audio Signal Processing (speech enhancement, microphone array), Natural Language Processing (machine translation, large language models), Machine Learning (deep learning, deep neural networks), and Multi-modal Foundation Models with applications in robotics, medicine, and education.
Full Professor,
Institute of Artificial Intelligence Innovation, Industry-Academia Innovation School, National Yang Ming Chiao Tung University
Email: yfliao (at) nycu.edu.tw,
Telephone: +886-3-5712121 ext. 58530
Address: ED-375, No. 1001， Daxue Rd. East Dist.， HsinChu, 300093， Taiwan
現職
陽明交大智能所教授，兼所長&人工智慧語音研究中心主任
陽明交大電機系合聘教授
教育部本國語文教育推動會委員
客委會諮詢委員
工研院資通所特聘研究 (顧問)
計算語言學學會，理事 & 口語小組召集人
- Consultant of ITRI since 2005
Media reports
- 族群媒體高峰會 Ethnic Media Summit 2023
projects
- PI：科技部華台語語音語料庫，兩年1,350萬(106~108)
- PI：教育部台語文語音語料庫，兩年1,000萬(108~111)
- CPI：經濟部旗艦科專，自然語言對話/圖像識別分項計畫，四年1億2206萬（107~111）
- CPI：客委會客語語音語料庫，兩年4,000萬(110~112)
- PI：教育部台語文語料庫，四年6,400萬(111~115)
- CPI：客委會客語語音語料庫，兩年5,780萬(112~114)
rewards
- Certificate of Appreciation for supporting the Live Subtitling of Central Epidemic Command Center (CECC)'s COVID-19 Press Conference (from 2020/4–2023/4), Taiwan, 2023.
近千場記者會都靠他們！指揮中心終場記者會 王必勝頒感謝狀給這「4」位 | 生活 | Newtalk新聞: https://newtalk.tw/news/view/2023-04-27/868574
【即時字幕】2023/4/27 14:00 中央流行疫情指揮中心嚴重特殊傳染性肺炎記者會: https://www.youtube.com/watch?v=JTGpwqONC_A
- Outstanding Industry-Academy Cooperation Award, NTUT, 2021
- 蒙古科技大學 (Mongolian University of Science and Technology, MUST)
- COVID-19 Response Award, Taiwan, 2020
Real-time subtitling technology for the press conference of CDC was awarded a certificate of appreciation by the President
- International Research Cooperation, Technical University of Kosice, Slovakia, 2019
http://kemt.fei.tuke.sk/organizacia/odborni-asistenti/matus-pleva
2017 Broadcast Golden Bell Awards（廣播金鐘獎）
Our Team received the "創新研發應用獎" (Technology Innovation Award) in the Broadcast Golden Bell Awards 2017 ceremony for Automatic Subtitling of Broadcast Radio Programs and Interactive Learning Systems.
- Outstanding Employee Award, Philips Research East Asia - Taipei, 2001
Guest editor of Special Issue of electronics
INTERNATIONAL BENCHMARKS
- The Oriental Language Recognition 2017 Challenge
Our team has been ranked the [3rd] out of 19 in the overall performance (average of the performance of all conditions in Cavg) ranking list, and the [4th], [2nd] and [2nd] out of 19 in the 1-, 3-second and full length utterance ranking list. Note: The submissions with a star after the team name is an extended submission. This means they should not be treated equally as the regular submissions (without a star).
- IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases
Our team NCTU-NTUT has be ranked the [4th] out of 19 with Mean-Ranked 6.5 out of 23 runs submissions.
- OC16 Chinese-English MixASR Challenge
Our deep LSTM-based ASR achieved overall performance Rank 2, English performance Rank 1 in the extended submission of OC16 Chinese-English MixASR Challenge
OTHER INTERNATIONAL BENCHMARKS
NIST Speaker Recognition Evaluation
NIST speaker recognition evaluation (SRE) 2010 （美國國家技術標準局語者辨認評比, http://www.itl.nist.gov/iad/mig//tests/sre/2010/index.html）
NIST language recognition evaluation (LRE) 2012 （美國國家技術標準局語言辨認評比，http://www.itl.nist.gov/iad/mig//tests/lre/2012/）
Speaker i-vector Machine Learning Challenge 2014（美國國家技術標準局語者辨認評比，https://ivectorchallenge.nist.gov）
Language Recognition Evaluation
NIST language recognition evaluation (LRE) 2009 （美國國家技術標準局語言辨認評比，http://www.itl.nist.gov/iad/mig//tests/lre/2009/）
NIST language recognition evaluation (LRE) 2011 （美國國家技術標準局語言辨認評比，http://www.itl.nist.gov/iad/mig//tests/lre/2011/）
Language i-vector Machine Learning Challenge 2015（美國國家技術標準局語言辨認評比，https://ivectorchallenge.nist.gov）
Blizzard Challenge (Text-to-Speech)
Blizzard Challenge 2009 （http://www.synsig.org/index.php/Blizzard_Challenge_2009）
Blizzard Challenge 2010 （http://www.synsig.org/index.php/Blizzard_Challenge_2010）
Blizzard Challenge 2012 （http://www.synsig.org/index.php/Blizzard_Challenge_2012）
Blizzard Challenge 2013 （http://www.synsig.org/index.php/Blizzard_Challenge_2013）
SIGHAN Bakeoff (Natural Language Processing)
SIGHAN Bakeoff 2012 Chinese Spelling Check
SIGHAN Bakeoff 2013 Chinese Spelling Check
SIGHAN Bakeoff 2014 Chinese Spelling Check
SIGHAN Bakeoff 2015 Chinese Spelling Check
Other Shared Tasks
NLP-TEA 2016 Shared Task: Chinese Grammatical Error Diagnosis (CGED)
IALP 2016 Shared Task: Dimensional Sentiment Analysis for Chinese Words