Yu Zhang Spoken Language Systems Group Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology office: 32-G442 email: yzhang87 at csail.mit.edu

About me

I am a graduate student working with Dr. James Glass. I primary focus on machine learning and its application to speech recognition, speaker verification and language identification.

Currently I participated in IARPA Babel Program which is a multi-lingual speech recognition project. I also try to apply deep neural network techniques to speaker verification and language identification.

Resume/CV

Here's my CV. [pdf]

Publications

• Highway Long Short-Term Memory RNNs for Distant Speech Recognition
  Yu Zhang, Guoguo Chen, Dong Yu, Kaisheng Yao, Sanjeev Khudanpur, James Glass
  arxiv:1510.08983, 2015.
• Prediction-adaptation-correction Recurrent Neural Networks for Low-resource Language Speech Recognition
  Yu Zhang, Ekapol Chuangsuwanich, James Glass, Dong Yu
  arxiv:1510.08985, 2015.
• An introduction to Computational Networks and the Computational Network Toolkit
  Dong Yu, Adam Eversole, Mike Seltzer, Kaisheng Yao, Zhiheng Huang, Brian Guenter, Oleksii Kuchaiev, Yu Zhang, Frank Seide, Huaming Wang, Jasha Droppo, Geoffrey Zweig, Chris Rossbach, Jon Currey, Jie Gao, Avner May, Baolin Peng, Andreas Stolcke, Malcolm Slaney
  Microsoft Technical Report MSR-TR-2014-112, 2014.
• Spoken Language Understanding using Long Short-Term Memory Neural Networks
  Kaisheng Yao, Baolin Peng, Yu Zhang, Dong Yu, Geoffrey Zweig, Yangyang Shi
  to appear in IEEE SLT, 2014.
• Language ID-based Training of Multilingual Stacked Bottleneck Features
  Yu Zhang, Ekapol Chuangsuwanich, James Glass
  Interspeech, 2014.
• Graph-based Re-ranking using Acoustic Feature Similarity between Search Results for Spoken Term Detection on Low-resource Languages
  Hung-yi Lee, Yu Zhang, Ekapol Chuangsuwanich, James Glass
  Interspeech, 2014.
• Recent Advances in ASR Applied to an Arabic Transcription System for Al-Jazeera
  Patrick Cardinal, Ahmed Ali, Najim Dehak, Yu Zhang, Tuka Hanai, Yifan Zhang, James Glass, Stephan Vogel
  Interspeech, 2014.
• Extracting deep neural network bottleneck features using low-rank matrix factorization
  Yu Zhang, Ekapol Chuangsuwanich, James Glass
  ICASSP, 2014.
• Joint Learning of Phonetic Units and Word Pronunciations for ASR
  Chia-ying Lee, Yu Zhang and James Glass.
  Empirical Methods in Natural Language Processing (EMNLP), 2013.
• Tied-state based discriminative training of context-expanded region-dependent feature transforms for LVCSR
  Zhi-Jie Yan, Qiang Huo, Jian Xu and Yu Zhang.
  ICASSP, 2013.
• A study of discriminative feature extraction for i-vector based acoustic sniffing in IVN acoustic model training
  Yu Zhang, Jian Xu, Zhi-Jie Yan and Qiang Huo.
  ICASSP, 2012.
• A new i-vector approach and its application to irrelevant variability normalization based acoustic model training
  Yu Zhang, Zhi-Jie Yan and Qiang Huo.
  Workshop on Machine Learning for Signal Processing (MLSP), 2011.
• An i-vector based approach to training data clustering for improved speech recognition
  Yu Zhang, Jian Xu, Zhi-Jie Yan, and Qiang Huo.
  Interspeech, 2011.
• An i-vector based approach to acoustic sniffing for irrelevant variability normalization based acoustic model training and speech recognition
  Jian Xu, Yu Zhang, Zhi-Jie Yan, and Qiang Huo.
  Interspeech, 2011.
• A study of irrelevant variability normalization based discriminative training approach for LVCSR
  Yu Zhang, Jian Xu, Zhi-Jie Yan, and Qiang Huo.
  ICASSP, 2011.
• Cross-validation based decision tree clustering for HMM-based TTS
  Yu Zhang, Zhi-Jie Yan, and Frank Soong.
  ICASSP, 2010.
• An evidence framework for Bayesian learning of continuous-density hidden Markov models
  Yu Zhang, Peng Liu, Jen-Tzung Chien, Frank K. Soong.
  ICASSP, 2009.

Technical Report

• Useful Derivations for i-Vector Based Approachto Data Clustering in Speech Recognition
  Yu Zhang, December 2011.
• A General Evidence Framework for Regularized Probabilistic Models
  Yu Zhang, Peng Liu, Jen-Tzung Chien, December 2010.

Teaching

• Fall 2009 Statistical Learning (TA)
  Professor: Liqing Zhang
  Book: The Elements of Statistical Learning