Qing Wang 王青  

National Engineering Laboratory for Speech and Language Information Processing (NELSLIP)
Department of Electronic Engineering and Information Science
University of Science and Technology of China (USTC)
No.96, JinZhai Road, Hefei, Anhui, 230026, China.

Research experience: Deep learning for robust speech recognition and speech enhancement, (2012~present)

• 12/2015~present: Research assistant at NELSLIP
  
  • Research on DNN learning behaviors, and propose explicit transformations in DNN-based speech enhancement.
    
  • Research on noise estimation, joint noise and mask aware training in DNN-based speech enhancement.
    
  • Research on multi-objective learning and ensembling architecture for high-performance speech enhancement.
    

• 9/2015~11/2015: Participating in the NIST Open Speech Activity Detection 2015 Evaluation (OpenSAD15)
  
  • Research on picking out regions of speech in an audio file.
    

• 5/2015~8/2015: Participating the 3rd CHiME Speech Separation and Recognition Challenge
  
  • Research on speech separation and recognition in challenging noisy environments recorded using a 6-channel tablet based microphone array.
    

• 1/2015~4/2015: Intern in iFlytek, Anhui
  
  • Research on acoustic modeling using long short-term memory based recurrent neural networks.
    

• 9/2012~12/2014：Research assistant at NELSLIP
  
  • Research on acoustic modeling with GMM-HMM and DNN-HMM for speech recognition.
    
  • Research on the complementary between different acoustic features based on deep neural networks for speech recognition.
    
  • Research on robust speech recognition with speech enhanced by DNN.
    
  • Research on voice activity detection based on jointly trained DNN.
    

Publications

• Qing Wang, Jun Du, Li Chai, Li-Rong Dai, and Chin-Hui Lee. A Maximum Likelihood Approach to Masking-based Speech Enhancement Using Deep Neural Network. Submitted to International Symposium on Chinese Spoken Language Processing (ISCSLP), TAIPEI, China, 2018.

• Qing Wang, Jun Du, Li-Rong Dai, and Chin-Hui Lee. A Multiobjective Learning and Ensembling Approach to High-Performance Speech Enhancement With Compact Neural Network Architectures. IEEE/ACM Transaction on Audio, Speech, and Language Processing [demo][pdf]

• Qing Wang, Jun Du, Li-Rong Dai, and Chin-Hui Lee. Joint Noise and Mask Aware Training for DNN-Based Speech Enhancement With Sub-band Features. Hands-free Speech Communication and Microphone Arrays (HSCMA), San Francisco, USA, 2017. [pdf]

• Qing Wang, Jun Du, Li-Rong Dai. Boosting DNN-Based Speech Enhancement via Explitcit Transformations.. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Jeju, Korea, 2016. [pdf]

• Jun Du, Qing Wang, Yan-Hui Tu, Xiao Bao, Li-Rong Dai, and Chin-Hui Lee. An Information Fusion Approach to Recognition Microphone Array Speech in the CHiME-3 Challenge Based on A Deep Learning Framework. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Scottsdale, USA, 2015. [pdf]

• Qing Wang, Jun Du, Xiao Bao, Zi-Rui Wang, Li-Rong Dai, and Chin-Hui Lee. A Universal VAD Based on Jointly Trained Deep Neural Networks. (INTERSPEECH), Dresden, Germany, 2015. [pdf]

• Qing Wang, Xia Wu, Jun Du, and Li-Rong Dai. Deep Neural Networks Based Feature Fusion for Noise Robust Speech Recogniton. National Conference on Man-Machine Speech Communication (NCMMSC), Tianjin, China, 2015. [pdf]

• Jun Du, Qing Wang, Tian Gao, Yong Xu, Li-Rong Dai, and Chin-Hui Lee. Robust Speech Recognition with Speech Enhanced Deep Neural Networks. (INTERSPEECH), Singapore 2014. [pdf]

Awards and honors

• Guanghua scholarship in USTC, 2016.

• Team score third place in CHiME-3 challenge, 2015.

• Best Student Paper Award Candidate, INTERSPEECH conference, 2015.