Number of pages 24 excluding figures and front matter Number of figures 7 Number of tables 9 Keywords robust ASR missing data data imputation HMM spectral subtraction

Abstract:  Human speech perception is robust in the face of a wide variety of distortions, both experimentally applied and naturally-occurring. In these conditions, state-of-the-art automatic speech recognition technology fails. This paper describes an approach to robust ASR which acknowledges the fact that some spectro-temporal regions will be dominated by noise. For the purposes of recognition, these regions are treated as missing or unreliable. The primary advantage of this viewpoint is that it makes minimal assumptions about any noise background. Instead, reliable regions are identified, and subsequent decoding is based on this evidence. We introduce two approaches for dealing with unreliable evidence. The first - marginalisation - computes output probabilities on the basis of the reliable evidence only. The second - statebased data imputation - estimates values for the unreliable regions by conditioning on the reliable parts and the recognition hypothesis. A further source of information is ...