Duc Le

Ph.D. Candidate

Computational Human-Centered Analysis and Integration Laboratory

Department of Electrical Engineering and Computer Science

University of Michigan, Ann Arbor

About Me

I am currently a 5th year Ph.D. student at the University of Michigan. I received my B.S. in Computer Science (summa cum laude) from the University of Texas at Dallas in May 2012 and M.S. in Computer Science from the University of Michigan in May 2014. I currently work with Professor Emily Mower Provost, specializing in speech recognition, computational paralinguistics, and speech-based assisitve technology for individuals with aphasia.

Before joining Michigan, I worked on speech emotion recognition in Professor Yang Liu's lab as an undergraduate research assistant. I interned at Amazon (Seattle, WA) as a software engineer in Summer 2011 and 2012, where I worked on automated UI testing with Ruby on Rails and helped develop the mobile authorization platform for Kindle devices.

In Summer 2015, I interned with Facebook's Language Technology Group (Menlo Park, CA), now a part of Applied Machine Learning, focusing on Deep Neural Network acoustic model adaptation for large-vocabulary speech recognition. I came back to Facebook in Summer 2016 for a return internship, working on end-to-end speech recognition and acoustic model compression.

**UPDATE** I graduated in August 2017 and currently work at Facebook as a Research Scientist.

Research

I have always been fascinated by the human mind and its relation to the computer's artificial brain. Broadly speaking, I am interested in using the computer's modeling power to better understand the inner workings of the human mind, and using this understanding to create more intelligent software programs. The aspect that I am most interested in is human speech, which not only encodes semantic content but also influences the perception of other people about the speaker, such as his/her emotion, competence, personality, eloquence, etc... I am interested in developing computational methods to model this kind of subjective perception. My current research interests include: machine learning in speech/language processing, computational paralinguistics, emotion recognition, speech-based assistive technology, and clinical applications.

Publications

Duc Le. "Towards Automatic Speech-Language Assessment for Aphasia Rehabilitation." Ph.D. Thesis. University of Michigan. August, 2017. [pdf]

Duc Le, Keli Licata, and Emily Mower Provost. "Automatic Paraphasia Detection from Aphasic Speech: A Preliminary Study." 18th Annual Conference of the International Speech Communication Association (INTERSPEECH). Stockholm, Sweden. August, 2017. (oral presentation) [pdf]

Duc Le, Zakaria Aldeneh, and Emily Mower Provost. "Discretized Continuous Speech Emotion Recognition with Multi-Task Deep Recurrent Neural Network." 18th Annual Conference of the International Speech Communication Association (INTERSPEECH). Stockholm, Sweden. August, 2017. (oral presentation) [pdf]

John Gideon, Biqiao Zhang, Zakaria Aldeneh, Yelin Kim, Soheil Khorram, Duc Le, and Emily Mower Provost. "Wild Wild Emotion: A Multimodal Ensemble Approach." ACM International Conference on Multimodal Interaction (ACM ICMI). Tokyo, Japan. November, 2016. [pdf]

Duc Le and Emily Mower Provost. "Improving Automatic Recognition of Aphasic Speech with Aphasia Bank." 17th Annual Conference of the International Speech Communication Association (INTERSPEECH). San Francisco, USA. September, 2016. [pdf]

Duc Le, Keli Licata, Carol Persad, and Emily Mower Provost. "Automatic Assessmsent of Speech Intelligibility for Individuals with Aphasia." IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2016. [pdf] [supplementary]

Duc Le and Emily Mower Provost. "Data Selection for Acoustic Emotion Recognition: Analyzing and Comparing Utterance and Sub-Utterance Selection Strategies." 6th International Conference on Affective Computing and Intelligent Interaction (ACII). Xi'an, China. September, 2015. (oral presentation) [pdf]

Duc Le and Emily Mower Provost. "Modeling Pronunciation, Rhythm, and Intonation for Automatic Assessment of Speech Quality in Aphasia Rehabilitation." 15th Annual Conference of the International Speech Communication Association (INTERSPEECH). Singapore. September, 2014. (oral presentation) [pdf]

Duc Le, Keli Licata, Elizabeth Mercado, Carol Persad, and Emily Mower Provost. "Automatic Analysis of Speech Quality for Aphasia Treatment." IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Florence, Italy. May, 2014. [pdf]

Duc Le and Emily Mower Provost. "Emotion Recognition from Spontaneous Speech using Hidden Markov Models with Deep Belief Networks." Automatic Speech Recognition and Understanding (ASRU). Olomouc, Czech Republic. December, 2013. [pdf]

Je Hun Jeon, Duc Le, Rui Xia, and Yang Liu. "A Preliminary Study of Cross-lingual Emotion Recognition from Speech: Automatic Classification versus Human Perception." 14th Annual Conference of the International Speech Communication Association (INTERSPEECH). Lyon, France. August, 2013. [pdf]

Contact

3945 Bob and Betty Beyster Building, University of Michigan, 2260 Hayward Street, Ann Arbor, MI 48109-2121

Email: ducle [at] umich [dot] edu