My current reserach focus in using content structure knowledge in limited resource spoken term detection. My advisor is Prof. Alex Rudnicky.
- PhD, Language Technology Institute, Carnegie Mellon University 2013-present
- M.S., Language Technology Institute, Carnegie Mellon University 2011-2013
- Research Area: Speech Processing, Spoken Term Detection
- Advisor: Prof. Alex Rudnicky
- B.S., Computer Science and Information Engineering (CSIE) ,National Taiwan University 2005-2009
- Selected Publication
- Ryan T.K. Lin, Justin Liang-Te Chiu, Hong-Jie Dai, Richard Tzong-Han Tsai, Min-Yuh Day, Wen-Lian Hsu, "A supervised learning approach to biological question answering", in the Integrated Computer-Aided Engineering, Volume 16, Number 3, 2009 [PDF]
- Ryan T.K. Lin, Hong-Jie Dai, Yue-Yang Bow, Justin Liang-Te Chiu, Richard Tzong-Han Tsai, "Using conditional random fields for result identification in biomedical abstracts", in the Integrated Computer-Aided Engineering, Volume 16, Number 4, 2009 [PDF]
- Justin Chiu, Alex Rudnicky, "Using Conversational Word Burst in Spoken Term Detection", in the Proceedings of Interspeech 2013, France [PDF]
- Sunayana Sitaram, Gopala Krishna Anumanchipalli, Justin Chiu, Alok Parlikar, Alan Black, "Text to Speech in New Languages without a Standardized Orthography", in the Proceedings of 8th ISCA Speech Synthesis Workshop, Spain [PDF]
- Aren Jansen, Emmanuel Dupoux, Sharon Goldwater, Mark Johnson, Sanjeev Khudanpur, Kenneth Church, Naomi Feldman, Hynek Hermansky, Florian Metze, Richard Rose, Mike Seltzer, Pascal Clark, Ian McGraw, Balakrishnan Varadarajan, Erin Bennett, Benjamin Borschinger,Justin Chiu, Ewan Dunbar, Abdellah Fourtassi, David Harwath, Chia-ying Lee, Keith Levin, Atta Norouzian, Vijay Peddinti, Rachael Richardson, Thomas Schatz, Samuel Thomas, "A Summary of The 2012 JHU CLSP Workshop on Zero Resource Speech Technologies and Models of Early Language Acquisition", in the Proceedings of the 38th International Conference on Acoustics, Speech, and Signal Processing, Canada [PDF]
- Justin Liang-Te Chiu, Jyun-Wei Huang, "Optimizing Language Model Information Retrieval System with Expectation Maximization Algorithm", in the Proceedings of ACL-IJCNLP 2009 Student Research Workshop, Singapore [PDF]
- Justin Chiu, "Using Conversational Word Burst in Spoken Term Detection", invited talk, University of Cambridge, 2013 [PPT]
- Justin Liang-Te Chiu, "Zero Resource Spoken Term Detection on STD 06 dataset", in the Mini-Workshop on Zero Resource Speech Technologies and Models of Early Language Acquisition, John Hopkins University, 2012 [PPT]
- Justin Liang-Te Chiu, "Explorations in Zero-Resource Spoken Term Detection", in the Student Research Symposium, Carnegie Mellon University, 2012 [poster]
- Honors and Awards
- Research Assistantship, Language Technology Institute, Carnegie Mellon University 08/2011-Present
- Been selected as graduate Research Assistant, tuition covered, stipend provided.
- Fellowship, Hong-Yang Culture & Education Foundation 2008, 2009
- Award for the undergraduate student with excellent performance
- Working Experience
- Research Assistant, Laboratory for Advanced Conversational Systems, Language Technology Institute, Carnegie Mellon University 08/2011-Present
- Developing portable speech recognition systems and language-independent speech recognition systems
- Research Assistant, Digital Speech Processing Lab, Department of Electrical Engineering, National Taiwan University 08/2010-07/2011
- Constructing a speech lecture system for Signal and System course.
- Second Lieutenant, Air Defense Artillery Platoon Leader, Republic of China Air Force, 08/2009-07/2010
- Trained and served as a Platoon Leader for the Air Defense Artillery.
- Part-time Research Assistant, Intelligent Agent System Lab, Institute of Information Science, Academia Sinica 07/2007-07/2009
- Building a biomedical Question Answering system and conducting NLP researches.
- Application Developed
- Summoner is a News summary reader. It will auto generate News summary with advanced Natural Language Processing algorithm, summarizing page-long news in several sentences.
- [link] to the app in the GooglePlay.
- Pocket Sphinx Demo
- It is an android-based portable Speech Recognizer with Sphinx Speech Recognition engine. It can provide real time Speech Recognition with onboard recognizer.
- Technical Skill
- C/C++, C#, Java, Python, Matlab, R, SQL, and UNIX shell scripting.
- Mandarin Chinese (native) and English (fluent)
- Yes, I looks totally like a Taiwanese boy, and I grew up in Taiwan, but I was born at Philadelphia.
- I had participated in different kind of activities, more diversities are always good for everyone.
- Model United Nations, Ballroom Dancing, Auspicing Radio Station, Swimming, Climbing, Application Developing, Traveling and Gaming etc...
- I wish to let every "tomorrow" beyond my imagination. Before I try to make the world better, I have to make myself better.