Handling Missing and Unreliable Information in Speech Recognition

  title={Handling Missing and Unreliable Information in Speech Recognition},
  author={Phil D. Green and Jon Barker and Martin Cooke and Ljubomir Josifovski},
In this work, techniques for classiication with missing or unreliable data are applied to the problem of noise-robustness in Automatic Speech Recognition (ASR). The primary advantage of this viewpoint is that it makes minimal assumptions about any noise background. As motivation, we review evidence that the auditory system is capable of dealing with incomplete data and, indeed, does so in normal listening conditions. We formulate the unreliable classiication problem and show how it can be… CONTINUE READING