A neural oscillator sound separator for missing data speech recognition

In order to recognise speech in a background of other sounds, human listeners must solve two perceptual problems. First, the mixture of sounds reaching the ears must be parsed to recover a description of each acoustic source, a process termed `auditory scene analysis´. Second, recognition of speech must be robust even when the acoustic evidence is missing due to masking by other sounds. This paper describes an automatic speech recognition system that addresses both of these issues, by combining a neural oscillator model of auditory scene analysis with a framework for `missing data´ recognition of speech