Sixth International Conference on Spoken Language Processing (ICSLP 2000)

Beijing, China
October 16-20, 2000

Soft Decisions in Missing Data Techniques for Robust Automatic Speech Recognition

Jon Barker, Ljubomir Josifovski, Martin Cooke, Phil Green

Department of Computer Science, University of Sheffeld, UK

In previous work we have developed the theory and demonstrated the promise of the Missing Data approach to robust Automatic Speech Recognition. This technique is based on hard decisions as to whether each time-frequency "pixel" is either reliable or unreliable. In this paper we replace these discrete decisions with soft estimates of the probability that each "pixel" is reliable. We adapt the probability calculation to use these estimates as weighting factors for the complementary reliable/unreliable interpretations for each feature vector component. Experiments using the TIDigits connected digit recognition task demonstrate that this technique a ords significant performance improvements at low SNRs.


Full Paper

Bibliographic reference.  Barker, Jon / Josifovski, Ljubomir / Cooke, Martin / Green, Phil (2000): "Soft decisions in missing data techniques for robust automatic speech recognition", In ICSLP-2000, vol.1, 373-376.