Acoustic Modeling for Large Vocabulary Speech Recognition

The field of large vocabulary, continuous speech recognition has advanced to the point where there are several systems capable of attaining between 90 and 95% word accuracy for speaker independent recognition, of a 1000 word vocabulary, spoken fluently for a task with a perplexity (average word branching factor) of about 60. There are several factors which account for the high performance achieved by these systems, including the use of hidden Markov model (HMM) methodology, the use of context-dependent sub-word units, the representation of between-word phonemic variations, and the use of corrective training techniques to emphasize differences acoustically similar words in the vocabulary. In this paper we describe one of the large vocabulary speech recognition systems which is being investigated at AT&T Bell Laboratories, and discuss the methods used to provide high word recognition accuracy.