1992 | OriginalPaper | Chapter
Developments in High-Performance Connected Digit Recognition
Authors : Yves Normandin, Régis Cardin
Published in: Speech Recognition and Understanding
Publisher: Springer Berlin Heidelberg
Included in: Professional Book Archive
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
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.