The Speech and Audio Technology Laboratory (SATLab) is committed to advancing the theory, methodologies, and practical applications within the domains of speech, audio, music, and auditory information processing. Our primary research focuses encompass speech recognition and analysis, audio recognition and analysis, as well as the processing of music and acoustic signals, complemented by our work in machine learning.

SATLab has spearheaded several pivotal projects supported by the National Natural Science Foundation of China and the National Key Research and Development Program of China. We have also achieved excellent results in a variety of speech and audio technology challenges.