About
          • Chengzhu Yu (俞承柱) (유승주) [My CV] [Citations]
          • Researcher at Tencent AI Lab in Seattle
          • Graduated with PhD from University of Texas at Dallas, July 2017 
          • Research interest:
            • Machine learning
            • Automatic Speech recognition
            • Voice biometric
            • Speaker diarization
 



Research Experience
  • Researcher at Tencent AI Lab, Seattle (July, 2017~ )
  • Research Intern at Siri, Apple, Cupertino (Jan, 2017 ~ May 2o17)
  • Research Intern at Microsoft Research, Redmond (May, 2016 ~ Aug 2016)                                         
  • Research Intern at NTT Communications Science Laboratories, Japan  (Jan, 2015 ~ May 2015)

Competition and Awards

  • CHIME-3 speech enhancement and recognition challenge (member of NTT) [Ranked #1] 
  • NIST 2015 I-Vector Machine Learning Language Recognition Challenge. (member of UTD-CRSS) [Ranked #3]
  • NIST 2014 I-Vector Machine Learning Speaker Recognition Challenge.(member of UTD-CRSS) 

Publications (selected)

G. Zweig, C. Yu, J. Droppo, A. Stolcke. "Advances in All-Neural Speech Recognition", in ArXiv, 2016 [PDF]

C. Yu, C. Zhang, F. Kelly, A. Sangwan, J. H. L. Hansen. "Text-available Speaker Recognition System For Forensic Applications", in Interspeech, 2016 [PDF]

 C. Yu, A. Ogawa, M, Delcroix, T. Yoshioka, T. Nakatani, J.H.L. Hansen, "Robust i-vector extraction for neural network adaptation in noisy environment", in Interspeech, Dresden, 2015 [PDF] [POSTER]

T. Yoshioka, N. Ito, M, Delcroix, A. Ogawa, K. Kinoshita, M. Fujimoto, C. Yu, W. Fabian, M. Espi, T. Higuchi, S. Araki, T. Nakatani, "The NTT CHIME-3 system: Advances in Speech Enhancement and Recognition for Mobile Multi-microphone Devices", in ASRU 2015 [PDF] [POSTER] [Best Paper Award Honorable Mention]

C. Yu, G. Liu, S. Hahm, and J. H. L. Hansen, "Uncertainty Propagation in Front End Factor Analysis For Noise Robust Speaker Recognition," in ICASSP, Florence, 2014. [VIEW] [PDF]



Publications (full)
C. Yu, J. H. L. Hansen. "A Study of Voice Production Characteristics of Astronaut Speech During Apollo 11 for Speaker Modeling in Space".  JASA, 2017


D. Wang, C. Yu, J. H. L. Hansen. "Robust Harmonic Feature for Classification Based Pitch Estimation". IEEE TASLP, 2017 

C. Yu, C. Zhang, S. Ranjian, Q. Zhang, A. Misra, F. Kelly, J. H. L. Hansen. "UTD-CRSS System For the NIST 2015 Language Recognition I-Vector Machine Learning Challenge"in ICASSP, 2016 [PDF]

M. Delcroix, K. Kinoshita, C. Yu, A. Ogawa, T. Yoshioka, T. Nakatani. "Context Adaptive Deep Neural Networks For Fast Acoustic Model Adaptation in Noisy Conditions"in ICASSP, 2016 [PDF]

S. Ranjan, C. Yu, C. Zhang, F. Kelly, J. H. L. Hansen. "Language Recognition Using Deep Neural Networks With Very Limited Training Data". in ICASSP, 2016

C. Yu, G. Liu, J. H. L. Hansen, "Acoustic Feature Transformation using UBM-based LDA for Speaker Recognition", in Interspeech, Singapore, 2014. [VIEW] [PDF] [Slides]

C. Yu, K. K. Wojcicki, M. Johnson, P. C. Loizou, J. H. L Hansen."Evaluation of the importance of time-frequency contributions to speech intelligibility in noise", JASA, 2014. [VIEW] [PDF]

C. Zhang, G. Liu, C. Yu, J.H.L. Hansen, "i-vector based physical stress detection with different fusion strategies", in Interspeech, Dresden, 2015 (accepted)

A. Shangwan, C. Yu, L. Kaushik, A. Ziaei, J.H.L. Hansen, "Speech processing technology for human behavior and performance monitoring: recent algorithmic advancements, solutions and challenges". NASA HRP Investigators' workshop: Integrated pathways to Mar, 2015 [VIEW][PDF]

G. Liu, C. Yu, N. Shokouhi, A. Misra, H. Xing, J. H. L. Hansen, "Utilization of unlabeled development data for speaker verification", SLT 2014, South Lake Tahoe, Nevada, Dec 7-10, 2014. [VIEW][PDF

C. Yu, J. H. L. Hansen, "Houston, we have a solution: A Case Study of the Analysis of Astronaut Speech During NASA Apollo 11 for Long-Term Speaker Modeling", in Interspeech, Singapore, 2014. [VIEW][PDF] [Slides]

G. Liu, C. Yu, A. Misra, N. Shokouhi, J. H. L. Hansen,"Investigating State-of-the-Art Speaker Verification in the case of Unlabeled Development Data", in Odyssey 2014.

A. Sangwan, L. Kaushik, C. Yu, J.H.L Hansen, and D. W. Oard. "‘Houston, We have a solution’: Using NASA Apollo Program to advance Speech and Language Processing Technology." in Interspeech, 2013. [pdf][bib]

C. Yu, K. K. Wójcicki, P. C. Loizou, and J.H.L Hansen. "A new mask-based objective measure for predicting the intelligibility of binary masked speech.". in ICASSP, 2013. [pdf][bib]


Publication (Under Review)

C. Yu,  J. H. L. Hansen. "Active Learning Based Constrained Clustering For Speaker Diarization".  submitted to IEEE TASLP, 2017

Others
  1. Study notes on the mathematical derivation of factor analysis for i-vector extraction [pdf].
Contact
  • email: cyu0913@gmail.com   chengzhu.yu@utdallas.edu
Subpages (1): publications