Welcome to my personal webpage!
I am a Master student in Language Technologies Institue of School of Computer Science at Carnegie Mellon University. My research interest includes machine learning application, multimedia analysis and indexing, speech and natural language processing.
I received my Bachelor degree in Electrical Engineering from Tsinghua University in 2012. I worked in Microsoft(Beijing) Speech group as a research intern during 2012 Feb to 2012 July.
More details can refer to my CV.
- Undergraduate (Tsinghua University)
Math: Calculus, Linear Algebra and Analytic Geometry, Complex Analysis, Methods of Math and Physics, Probability and Statistics, Stochastic Process.
Signal Processing: Signals and Systems, Digital Signal Processing, Speech Signal Processing.
Algorithm: Data structure, Numeric Analysis and Algorithms, Pattern Recognition.
- Graduate(Carnegie Mellon University)
Introduction to Machine Learning (for Phd),
Probabilistic Graphical Model
Theory and practice of speech recognition systems,
Algorithms for NLP,
Software Engineering for Information Systems
- Yipei Wang, Shourabh Rawat, Florian Metze Semi-automatic Audio Semantic Concept Discovery for Multimedia Retrieval accepted to 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Yipei Wang, Shourabh Rawat, Florian Metze Exploring Audio Semantic Concepts for Event-based Video Retrieval accepted to 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Zhen-Zhong Lan, Lu Jiang, Shoou-I Yu, Chenqiang Gao, Shourabh Rawat, Yang Cai, Shicheng Xu, Haoquan Shen, Xuanchong Li, Yipei Wang, Waito Sze, Yan Yan, Zhigang Ma, Nicolas Ballas, Deyu Meng, Wei Tong, Yi Yang, Susanne Burger, Florian Metze, Rita Singh, Bhiksha Raj, Richard Stern, Teruko Mitamura, Eric Nyberg, and Alexander Hauptmann, Informedia E-lamp@TRECVID 2013 Multimedia Event Detection and Recounting. TRECVID 2013 Video Retrieval Evaluation workshop
- Efficient Algorithm for Distance Metric Learning (course: convex optimization 11-725)
- Implemetation of digit speech recognizer (course: Theory and practice of speech recognition systems)
- Semi-supervised method for prosody detection(internship in Microsoft)
[technical report](The experiment is conducted on the internal data and I am not allowed to distribute the content of the report. Attached is only the table of contents of the report.)
- Multimedia Event Detection
Explored speech transcription [report summary]
Explored semantic concepts [report summary]
CMU ranked 1st in audio-contrastive run TRECVID 2013 evaluation!
- Natural Language Understanding for situated dialogue (car enviroment)
Investigate multi-modalities for reference resolution (transcripts, gesture, prosodic feature) ...
Activities Beyond Academia
My childhood dream is to become a journalist. I published multiple literature articles on the school magzine when I was in high school. I finally realized my dream by joining the campus newspaper after I entered into college. It provides me many opportunities to interview the students or faculties with interesting stories. I feel happy to help people by making their voice heard.
I am a sports fan. I started to practice martial arts since I was in middle school and won several prizes in the matches in college. I learned a lot beyond building the body, including the rich tradional Chinese culture and the spirit of courage and peaceful mind in facing challenges. I once completed half marathon in 2010 fall.
I enjoy travel, which provides a way to listen to the voice in my heart when emerging into a strange environment. I love painting and received formal training when I was young. But as I grow up, I start to realize that the real beauty origins from people's heart and creative view to discover the world rather than the fancy skills.