Home

Emailcweng6 [at] gmail [dot] com

Backgrounds

Chao is currently a Speech Research & Dev. Engineer in Siri team at Apple Inc. Prior to joining Apple, he has been conducting research on many aspects of speech recognition for years at Georgia Tech advised by Prof. Biing-Hwang (Fred) Juang. He has also been with AT&T Lab Research and Microsoft Research as a Research Intern, working on recurrent neural network language modeling, Mandarin and Japanese speech recognition, deep neural networks for multi-talker speech recognition. Chao contributes to the Kaldi project (cf. the project page) , a popular open-source speech recognition toolkit that has been widely adopted by academia and industry. His backgrounds lie generally in the areas of speech recognition and natural language processing with special focus on discriminative training, recurrent neural networks, far-field speech recognition, weighted finite-state transducers (WFSTs) for speech and language processing. Chao holds a Ph.D. in Electrical and Computer Engineering from Georgia Institute of Technology.

Educations

Ph.D., Electrical and Computer Engineering, Georgia Institute of Technology, 2014
- Dissertation: Towards Robust Conversational Speech Recognition and Understanding (pdf)
M.S., Electrical and Computer Engineering, Georgia Institute of Technology, 2010
M.S., Electrical Engineering, Shanghai Jiao Tong University, 2010
B.S., Electrical Engineering, East China University of Science and Technology, 2007

Experiences 

Speech Research & Dev. Engineer, Siri at Apple, Cupertino, CA, Aug. 2014 - 
Research Assistant, Georgia Institute of Technology, Atlanta, GA,  Jan. 2010 - July. 2014
---Advisor: Biing-Hwang (Fred) Juang
Research Intern, Microsoft Research, Redmond, WA,  May. 2013 - Aug. 2013
---Mentor: Dong Yu, Mike Seltzer, Jasha, Droppo
Research Intern, AT&T Labs Research, Florham Park, NJ,  May. 2012 - Aug. 2012
---Mentor: David Thomson, Patrick Haffner, Diamantino Caseiro

Publications

[1] C. Weng, D. Yu, M. L. Seltzer and J. Droppo, "Deep Neural Networks for Single-Channel Multi-Talker Speech Recognition," Audio, Speech, and Language Processing, IEEE/ACM Transactions on, vol.23, no.10, pp.1670,1679, Oct. 2015 

[2] C. Weng and B.-H. Juang, "Discriminative Training Using Non-Uniform Criteria for Keyword Spotting on Spontaneous Speech," Audio, Speech, and Language Processing, IEEE/ACM Transactions on, vol.23, no.2, pp.300,312, Feb. 2015

[3] C. Weng, D. Thomson, P. Haffner and B.-H. Juang, "Latent Semantic Rational Kernels for Topic Spotting on Conversational Speech," Audio, Speech, and Language Processing, IEEE/ACM Transactions on , vol.22, no.12, pp.1738,1749, Dec. 2014

[4] Z. Huang, J. Li, C. Weng and C.-H Lee, "Beyond Cross-entropy: Towards Better Frame-level Objective Functions For Deep Neural Network Training In Automatic Speech Recognition", in Proc. InterSpeech2014

[5] Z. Huang, J. Li, S. Siniscalchi, I. Chen, C. Weng and C.-H Lee, "Feature Space Maximum A Posteriori Linear Regression for Adaptation of Deep Neural Networks", in Proc. InterSpeech2014

[6] C. Weng, D. Yu, S. Watanabe and B.-H. Juang, "Recurrent Deep Neural Networks for Robust Speech Recognition" in Proc. ICASSP2014 (pdf, code)

[7] C. Weng, D. Yu, M. L. Seltzer and J. Droppo, "Single-channel Mixed Speech Recognition Using Deep Neural Networks" in Proc. ICASSP2014 (pdf)

[8] Z. Huang, C. Weng, K. Li, Y. Cheng and C.-H. Lee, "Deep Learning Vector Quantization for Acoustic Information Retrieval" in Proc. ICASSP2014 (pdf)

[9] C. Weng and B.-H. Juang, "Latent Semantic Rational Kernels for Topic Spotting on Spontaneous Conversational Speech", in Proc. ICASSP2013. (pdf)

[10] C. Weng and B.-H. Juang, "Adaptive Boosted Non-uniform MCE for Keyword Spotting on Spontaneous Speech", in Proc. ICASSP2013. (pdf)

[11] C. Weng, B.-H. Juang and D. Povey, "Discriminative Training Using Non-uniform Criteria for Keyword Spotting on Spontaneous Speech", in Proc. InterSpeech2012. (pdf)

[12] C. Weng and B.-H. Juang, "A Comparative Study of Discriminative Training Using Non-uniform Criteria for Cross-layer Acoustic Modeling", in Proc. ICASSP2012. (pdf)

[13] C. Weng and B.-H. Juang, "Recent development of discriminative training using non-uniform criteria for cross-level acoustic modeling", in Proc. ICASSP2011. (pdf)

Patents
[1] D. Yu, C. Weng, M. L. Seltzer, J. Droppo, “Mixed Speech Recognition”  US20160284348 A1