These days speech recordings from mobile phones are increasingly being used human machine interfaces. One of the things about mobile phones is that people can move around considerably as they speak into their phones. The question is how much does this physical activity impact on the speech signal, since the breathing mechanism is also tied in with the speech mechanism. This project will involve creating a corpus of speech when people are moving and then directly measuring the glottal pulse extracted from the speech signal. Comparison of the glottal pulse with the speaker in different modes of movement will be investigated. The findings from this project have implications for speech forensics, speaker recognition, speech recognition and speech coding
Undergraduate
None
Lab allocations have not been finalised