Speech and Audio Signal Processing Lab

Speech, Music and other Audio signals define and influence a large part of human cognitive experience. Speech/Music compression for communication/storage, automatic speech/music recognition/classification for man-machine interaction, speech/music enhancement in noise/interference/disability, multi-channel sound source localization and sound field rendering are type of problems that we address using the technologies of signal processing and pattern recognition, which is both exciting, challenging and rewarding.

These topics touch science at one end (perception/cognition) and technology products (robots) at the other end, with many intermediary solutions.

Research facilities in the speech and audio signal processing lab are guided by Prof. T V Sreenivas.