September 22-25, 1997
Speech recognition performance degrades significantly when a mismatch occurs between training and operating conditions. To reduce this mismatch, it is often necessary to characterize the mapping between two environments. A number of statistical approaches have been developed for this purpose. They can be classified as either predictive or adaptive, depending on what information is available regarding the operating environment. This paper reviews a selected subset from both categories, and discusses possible future directions of improvement.
Bibliographic reference. Bellegarda, Jerome (1997): "Statistical techniques for robust ASR: review and perspectives", In EUROSPEECH-1997, KN33-KN36.