Description
Instructor(s)/Supervisor(s)/Coordinator(s): Wei XUEThis course comprehensively introduces audio processing techniques, including audio enhancement and separation, recognition, and synthesis. Students will learn the fundamentals of audio transformations, exploring techniques such as the Short-Time Fourier Transform (STFT) and Mel Frequency Cepstral Coefficients (MFCCs), which are critical for understanding and manipulating audio data. The course will also cover advanced topics: a) Audio enhancement and separation for improving audio quality. b) Speech recognition, which transcribes audio into text. c) Speaker verification, which determines speaker identity. d) Sound event detection, which detects the presence of sound events in audio signals. e) Audio synthesis, which generates new audio based on control parameters. Evaluation will be based on assignments covering audio processing concepts and hands-on projects. Students are expected to have a basic understanding of machine learning to select this course.