Skip to content

Hongjiang Yu

Education
2016.09-present mkdocs Concordia University
Department of Electrical and Computer Engineering		 Ph.D
2012.09-2016.06 mkdocs Wuhan University
National Engineering Research Center
for Multimedia Software (NERCMS)		 Master
2008.09-2012.06 mkdocs Wuhan University
Electrical Information School		 Bachelor

Research Interest: Speech and Audio processing, including Speech Enhancement, Objective Quality Assessment and Bandwidth Extension

Research Experience
Concordia University Graduate Researcher 2016.09-present
  • Participated a NSERC CRD Grant project on deep neural network (DNN) based speech enhancement for robust speech recognition in smart home device
  • Developed a DNN assisted Kalman filtering system for time-domain speech denoising
  • Proposed a fully convolutional neural network to restore the complex spectrogram of the clean speech from that of the noisy speech
  • Collaborated with the research team in McGill university and researchers in Microchip company
Wuhan University Graduate Researcher 2012.09-2016.06
  • Participated a project on audio quality assessment based on auditory attention (supported by the National Natural Science Foundation of China)
  • Improved the performance of the traditional audio quality assessment system (PEAQ: perceptual evaluation of audio quality) by introducing psychological selective mechanism
  • Achieved the first prize in the National Postgraduate Mathematical Contest in modeling, with a model of fast time-varying channel modeling in wireless communication
  • Achieved the third prize in the National Postgraduate Electronic Design Contest, with a home-based care platform for the aged using speech emotion recognition

Leadship
Student Union of NERCMS President 2013.09-2014.06
  • Managed the educational and social routines for about 20 graduate students
  • Organized the entertainment activities of NERCMS, including the Spring Festival Gala

Publication Google Scholar

♦ Journal Paper

[1]. H. Yu, W.-P. Zhu, and B. Champagne. “Speech Enhancement Using a DNN-Augmented Colored-Noise Kalman Filter.” Speech Communication, 2020. (In Press) Code

[2]. H. Yu, Z. Ouyang, W.-P. Zhu and B. Champagne. “A Hybrid Speech Enhancement System with DNN Based Speech Reconstruction and Kalman Filtering.” Multimedia Tools and Applications, vol. 79, pp. 32643-32993, 2020.

♦ Conference Paper

[1]. H. Yu, W.-P. Zhu, and B. Champagne. “Subband Kalman Filtering with DNN Estimated Parameters for Speech Enhancement.” INTERSPEECH, pp. 2697-2740 2020.

[2]. H. Yu, W.-P. Zhu, and Y. Yang. “Constrained Ratio Mask for Speech Enhancement Using DNN.” INTERSPEECH, pp.2427-2431, 2020.

[3]. H. Yu, W.-P. Zhu, and B. Champagne. “High-frequency Component Restoration for Kalman Filter Based Speech Enhancement.” IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5, 2020.

[4]. H. Yu and W.-P. Zhu. “Deep Neural Network Based Complex Spectrogram Reconstruction for Speech Bandwidth Expansion.” IEEE International New Circuits and Systems Conference (NEWCAS), pp. 110-113. 2020.

[5]. H. Yu, Z. Ouyang, W.-P. Zhu, B. Champagne, and Y. Ji. “A Deep Neural Network Based Kalman Filter for Time Domain Speech Enhancement.” IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5. 2019. Code

[6]. Z. Ouyang, H. Yu, W.-P. Zhu and B. Champagne. “A Fully Convolutional Neural Network for Complex Spectrogram Processing in Speech Enhancement.” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5756-5760. 2019. Slides

[7]. Z. Ouyang, H. Yu, W.-P. Zhu and B. champagne. “A Deep Neural Network Based Harmonic Noise Model for Speech Enhancement.” INTERSPEECH, pp. 3224-3228. 2018.

[8]. Y. Yang, H. Yu, R, Hu, et al. “Auditory Attention Based Mobile Audio Quality Assessment.” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1389-1393. 2014.

Award
Concordia Merit Scholarship Concordia University 2016-2017
Concordia International Tuition Award of Excellence Concordia University 2016
National Scholarship for Postgraduate Students
(Top 1%, 2 times)		 China 2014, 2015
Outstanding Graduates (Top 10%, 2 times) Wuhan University 2012
The Second Prize Scholarship (Top 10%, 2 times) Wuhan University 2009, 2011

Skill & Interest

  • Knowledge: professional in the research area of audio/speech signal processing and neural networks, with the capability of algorithm design and system integration
  • Programming: mastered at programming with Matlab and Python
  • Computer: familiar with the DNN framework TensorFlow and the audio analysis software Audition
  • Language: full professional proficiency in English and native speaker in Chinese
  • Interest: jogging, swimming and volleyball