Developments in High-Performance Connected Digit Recognition

Recent advances in Hidden Markov Model (HMM) based speaker-independent connected digit recognition have usually tended to make the models more complex. This paper concentrates on improving the training techniques in order to make the most of the available parameters. A new algorithm, Corrective MMI Training is introduced. Use of this algorithm resulted in significant improvements in our recognition rates. We now obtain less than 2% string error rate using semi-continuous HMMs with two models per digit.