This is SUSTech Audio Intelligence Lab (SAIL, 南科大音频智能实验室) directed by Prof. Zhong-Qiu Wang in the Department of Computer Science and Engineering at Southern University of Science and Technology (SUSTech) in Shenzhen, China.

We are interested in broad speech/audio signal processing and artificial intelligence problems, aiming at building machine listening systems that can robustly perceive and understand speech/audio and interact with humans in noisy-reverberant environments with multiple concurrent sound sources. Our current research focuses on:

• Speech and audio processing
  ○ Speech separation (e.g., speaker separation, speech enhancement, and speech dereverberation)
  ○ Target sound extraction (e.g., embedding based TSE, audio-visual TSE, language-queried TSE)
  ○ Sound understanding (e.g., sound event detection, audio tagging, and sound separation)
  ○ Assistive hearing (e.g., hearing aids design, audiometer design, and smart hearables)
  ○ Real-time speech communication (e.g., acoustic echo cancellation, speech codec, and bandwidth extension)
  ○ Robust automatic speech recognition (e.g., noise-robust and multi-speaker ASR)
  ○ Microphone array signal processing (e.g., acoustic beamforming and sound source localization)
  ○ Generative models
  ○ Computer audition
• Deep learning
• Artificial intelligence

Our research is supported by National Natural Science Foundation of China, National Key Research and Development Program of China, and our industrial partners including Elevoc, OPPO and Huawei.