Speech processing and technology
In-depth studies into aspects of speech and human biometrics.
Our research facilities include a whisper room for anechoic recordings and speech database perpetration, multichannel data acquisition systems, acoustic head to study the actual human auditory hearing characteristics, sophisticated microphones and recording equipment.
This equipment is used to study speech signal parameterization, speaker recognition, speech recognition, speech synthesis, accent change, phonetic analysis, speech enhancement and noise control, audio watermarking, and forensic speech.
Our equipment can also be used to study human biometrics in a broader sense including the recognition of fingerprints, gait, lips, signature, palm veins, and palm geometry.