The overall scientific objectives of HOARSE are to gain a better understanding
of speech production and hearing and to use this understanding to explain
the perceptual organisation of sound and improve speech technology. The
project has five inter-related themes, addressing the following questions:
How are sound mixtures perceptually organised, and how can this Auditory
Scene Analysis can be used in speech recognition?
How does the Auditory System handle reverberant conditions, and
how can models of this processing be used for speech enhancement?
How is speech production related to speech perception and cerebral
speech processing, and how can this knowledge be integrated into speech
How can Automatic Speech Recognition algorithms take advantage of
the work in Themes 1 and 2, for use in natural listening conditions?
How can the results of other themes be exploited in speech recognition
applications which require robust performance in adverse conditions
and/or processing of sound mixtures?