cambridge_university
Your Name

Yu Wang 王钰


Senior Research Associate in Speech Processing

Yu Wang is a Senior Research Associate working in the Speech Group of the Machine Intelligence Laboratory, Engineering Department of University of Cambridge (CUED). He obtained his Bachelor degree at Huazhong University of Science and Technology in 2009 and his M.Sc. degree at Imperial College London. Following that, he did his PhD study in Audio Signal Processing in the Speech and Audio Processing Laboratory at Imperial College London and obtained his PhD degree in August, 2015, supervised by Mike Brookes. Following his graduation of PhD, he joined the Machine Intelligence Laboratory in CUED and started to work on the Automated Language Teaching and Assessment (ALTA) project which is funded by Cambridge Assessment. From September 2019, he also started to work on the Machine Translation for English Retrieval of Information in Any Language (MATERIAL) project (funded by IARPA), on which he is the technical lead for the CUED speech recognition contribution.

From April to July 2014, he was a Research Internship at Nuance Communication and was working on non-intrusive speech quality and intelligibility assessment, supervised by Dr Dushyant Sharma and Professor Patrick Naylor.

He is a member of IEEE, ISCA and a regular reviewer of major speech processing-related journals and conferences. He also served as the session chairs for some major conferences in speech and language processing.

 

Research Interests:

Speech and audio signal processing

  • Single and multi-channel speech enhancement
  • Non-intrusive speech quality and intelligibility assessment

Speech recognition

  • Acoustic model adaptation and combination
  • Speech recognition systems for spoken language assessment
  • Robust distant speech recognition
  • Teacher-student training for acoustic modeling
  • Recurrent neural network-based Language modeling

Automatic language assessment and education

  • Automatic non-native spoken language grading system
  • Grammatical error detection and correction
  • L1 detection and speaker verification for non-native English
  • Off-topic response detection

 

Education:

Huazhong University of Science and Technology,Department of EIE

Bachelor of Engineering (BEng), 2005 — 2009


Imperial College London,Department of EEE

Master of Science (MSc), 2009 — 2010


Imperial College London,Department of EEE

Doctor of Philosophy (PhD), 2011 — 2015

 

Publications:

Journal articles


  • Jeremy Wong, Mark,Gales, Yu Wang, “General sequence teacher-student learning”, IEEE/ACM Tranactions on Audio, Speech and Language Processing, vol. 27, no.11, pp. 1725–1736, November 2019.
  • Xie Chen, Xunying Liu, Yu Wang, Anton Ragni, Mark Gales, “Exploiting future word contexts in neural network language model”, IEEE/ACM Tranactions on Audio, Speech and Language Processing, vol. 27, no. 9, 1444–1454, September 2019.
  • Yu Wang , Mark Gales, Kate Knill et al, “Towards automatic assessment of spontaneous spoken English”, Speech Communication, vol. 104, pp. 47–56, November 2018.
  • Yu Wang and Mike Brookes, “Model based speech enhancement in the modulation domain”, IEEE/ACM Tranactions on Audio, Speech and Language Processing, vol. 26, no. 3, pp. 580–594, March 2018.
  • Dushyant Sharma, Yu Wang, Patrick Naylor, Mike Brookes, “A data-driven non-intrusive measure of speech quality and intelligibility”, Speech Communication, vol. 80, pp. 84–94, June 2016.

Conference papers


  • Jeremy Wong, Mark Gales, Yu Wang “Learning between different teacher and student models in ASR”, in Proc. IEEE ASRU Workshop, December 2019.
  • Linin Wang, Yu Wang, Mark Gales, "Non-native speaker verification for spoken language assessment", arXiv preprint, arXiv:1909.13695 .
  • Yiting Lu, Kate Knill, Mark Gales, Potsawee Manakul, Yu Wang, "Disfluency detection for spoken learner English", in Proc. ISCA International Workshop on Speech and Language Technology in Education (SLaTE), 2019.
  • Yiting Lu, Mark Gales, Kate Knill, Potsawee Manakul, Linin Wang, Yu Wang, "Impact of ASR performance on spoken grammatical error detection", in Proc. Interspeech, 2019.
  • Dushyant Sharma, Aidan Hogg, Yu Wang, Amr Nour-Eldin, Patrick A. Naylor, "Non-Intrusive POLQA Estimation of Speech Quality using Recurrent Neural Networks", in European Signal Processing Conference (EUSIPCO), 2019.
  • Yu Wang, Jeremy Wong, Mark Gales, Kate Knill, Anton Ragni, "Sequence teacher-student training of acoustic models for automatic free speaking language assessment", in Proc. IEEE Spoken Lauguage Techology (SLT) Workshop, December 2018.
  • Anton Ragni, Qiujia Li, Mark Gales, Yu Wang, "Confidence estimation and deletion prediction using bidirectional recurrent neural networks", in Proc. IEEE Spoken Lauguage Techology (SLT) Worshop, December 2018
  • Yu Wang, Chao Zhang, Mark Gales, Phil Woodland, “Speaker adaptation and adaptive training for jointly optimised Tandem systems”, in Proc. Interspeech, September 2018
  • Kate Knill, Mark Gales, Koastas Kyriakopoulos, Anrey Malinin, Anton Ragni, Yu Wang, and Andrew Caines, “Impact of ASR performance on free speaking language assessment”, in Proc. Interspeech, September 2018
  • Yu Wang, Xie Chen, Mark Gales, Anton Ragni, Jeremy Wong, “Phonetic and graphemic systems for multi-genre broadcast transcription”, in Proc. ICASSP, April 2018.
  • Xie Chen, Xunying Liu, Anton Ragni, Yu Wang, Mark Gales “Future Word Contexts in Neural Network Language Models”, in Proc. IEEE ASRU Workshop, December 2017.
  • Andrey Malinin, Kate Knill, Anton Ragni, Yu Wang, Mark Gales, “An attention-based model for off-topic spontaneous spoken response dection: An Initial Study”, in Proc. ISCA International Workshop on Speech and Language Technology in Education (SLaTE), August 2015.
  • Kate Knill, Mark Gales, Koastas Kyriakopoulos, Yu Wang, “Use of Graphemic Lexicons for Spoken Language Assessment”, in Proc. Interspeech, August 2017.
  • Andrey Malinin, Rogier van Dalen, Yu Wang, Kate Knill, Mark Gales, “Off-topic Response Detection for Spontaneous Spoken English Assessment”, in Proc. Association for Computational Linguistics (ACL) (Long paper), August 2016.
  • Yu Wang and Mike Brookes, “Speech enhancement using an MMSE spectral amplitude estimator based on a modulation domain Kalman filter with a Gamma prior”, in Proc. ICASSP, March 2016.
  • Yu Wang and Mike Brookes, “Speech enhancement using a modulation domain Kalman filter post-processor with a Gaussian Mixture noise model”, in Proc. ICASSP, April 2014.
  • Yu Wang and Mike Brookes, “A subspace method for speech enhancement in the modulation domain”, in Proc. European Signal Processing Conference (EUSIPCO), September 2013.
  • Yu Wang and Mike Brookes, “Speech Enhancement using a robust Kalman filter Post-processor in the modulation domain”, in Proc. ICASSP, March 2013.

PhD Thesis


 

Contact Infromation:

Yu Wang


Baker Building, Room BE4-58
Engineering Department
Trumpington Street, Cambridge
CB2 1PZ, UK

Email: yw396@cam.ac.uk