Hi. I'm Fei Tao.

I have been a Ph.D. Student at Multimodal Signal Processing (MSP) Lab in The University of Texas at Dallas since 2013. My supervisor is Dr. Carlos Busso. My research of interests includes:
Audiovisual Speech Recognition
Image and Speech Processing
Machine Learning and Data Mining

Learn about my work

Publications

Journal:

1. Tao, F., Busso, C. Gating Neural Network for Large Vocabulary Audio-Visual Speech Recognition System. Accepted by IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING.<\br>

Conference:

1. Tao, F. and Busso, C. Lipreading Approach for Isolated Digits Recognition under Whisper and Neutral Speech. 15th Annual Conference of the International Speech Communication Association (INTERSPEECH), Sep. 2014, Singapore.
2. Tao, F., Hansen, J. H., and Busso, C. An Unsupervised Visual-only Voice Activity Detection Approach Using Temporal Orofacial Features. In 16th Annual Conference of the International Speech Communication Association.
3. Tao, F., Daudet, L., Poellabauer, C., Schneider, S. L., and Busso, C. A Portable Automatic PA-TA-KA Syllable Detection System to Derive Biomarkers for Neurological Disorders. In 17th Annual Conference of the International Speech Communication Association.
4. Tao, F., Hansen, J. H., and Busso, C. (2016). Improving Boundary Estimation in Audiovisual Speech Activity Detection Using Bayesian Information Criterion. In 17th Annual Conference of the International Speech Communication Association.
5. Li, N., Misu, T., and Tao, F. Connecting Driver with Vehicle and Driving Environment using the Manifold Representation of Driver Physiological Signals. Submitted to the 22nd International Conference on Digital Signal Processing (DSP 2017).
6. Li, N., Misu, T., and Tao, F. Understand driver awareness through brake behavior analysis: Reactive versus intended hard brake. 2017 IEEE Intelligent Vehicles Symposium (IV).
7. Tao, F., Busso, C. Bimodal Recurrent Neural Network for Audiovisual Voice Activity Detection. . In 18th Annual Conference of the International Speech Communication Association. Aug. 2017, Stockholm, Sweden.
8. Bokshi, M., Tao, F., Busso, C. and Hansen, J. Assessment and Classification of Singing Quality Based on Audio-Visual Features to iThenticate. In 2017 IEEE Visual Communications and Image Processing.
9. Tao, F., Liu, G. and Zhao, Q. An Ensemble Framework of Voice-Based Emotion Recognition System for Films And TV Programs. Accepted by ICASSP 2018.
10. Tao, F. and Liu, G. Advanced LSTM: A Study about Better Time Dependency Modelling in Emotion Recognition. Accepted by ICASSP 2018.
11. Tao, F. and Busso, C. Aligning Audiovisual Features for Audiovisual Speech Recognition. Submitted to IEEE International Conference on Multimedia and Expo (ICME) 2018.
12. Tao, F., Liu, G. and Zhao, Q. An Ensemble Framework of Voice-Based Emotion Recognition System. Accepted by Asia ACII 2018.

Patent:

1. Li, N., Misu, T., and Tao, F. Understand driver awareness through brake behavior analysis. Submitted to U.S.A National Patent.<\br>

Project:

1. Speech Recognition System for SAMSUNG Mobile Devices. 2013 - 2014.
2. Automatic Speech Recognition System for Concussion Estimation. 2014.

Resources

I will share some tools and materials here that I developed. Now it is under construction.

The MSP

This is the team of my "phd" lab. I like the lab. The people here are very nice. I learn a lot from them. We are making cool stuff.

More about me

Personal

Brief Introduction

I am a Ph.D. student and research assistant at Multimodal Signal Processing (MSP) Lab, UT Dallas, since 2013. My supervisor is Dr. Carlos Busso. I obtained my B.S. degree from Beijing Jiaotong University, Beijing, China in 2009. Then I became a research assistant in the transportation department at Texas Southern University, focusing on Intelligent Transportation System (ITS). My current research of interests mainly includes audiovisual speech recognition, image and speech processing, machine learning and data mining. My resume is abailable here.

Hobbies and Interests

I am big fan of sports. I like to play badminton and bascketball. I also enjoy watching soccer game. I like Chinese ancient poems. Sometimes, I poetize.In the aspect of academic, I like history (prefer Chinese), theoretical physics, financial theory and econimic theory.

Contacts

Mail Address:

800 West Campbell Road, EC33
Richardson, TX 75080-3021

Office Address:

800 West Campbell Road, ECSN 4.410
Richardson, TX 75080-3021

Email:

fxt120230@utdallas.edu