Automatic speech recognition: a communication perspective

Speech recognition is usually regarded as a problem in the field of pattern recognition, where one first estimates the probability density function of each pattern to be recognized and then uses Bayes theorem to identify the pattern which provides the highest likelihood for the observed speech data. In this paper, we take a different approach to this problem. In speech recognition, the goal is communication of information by voice and we discuss the basics of speech recognition from a communication perspective. The speech signal at the acoustic level has a bit rate of 64 kb/s but the underlying sound patterns have an information rate of less than 100 b/s. What is the role of this high bit rate at the acoustic level? We discuss the principles of decoding patterns that are submerged in an ocean of seemingly irrelevant information