Automatic transcription of conversational telephone speech: development of the CU-HTK 2002 system
Thomas Hain, PC Woodland, G. Evermann, Mark Gales, X Liu, G.L. Moore, Daniel Povey, L Wang · Cambridge University Engineering Department Publications Database · 2003
This paper discusses the Cambridge University HTK (CU-HTK) system for the automatic transcription of conversational telephone speech. A detailed discussion of the most important techniques in front-end processing, acoustic modelling and model training, language and pronunciation modelling are presented. These include the use of conversation side based cepstral normalisation, vocal tract length normalisation, heteroscedastic linear discriminant analysis for feature projection, Minimum Phone Error Training and speaker adaptive training, latticebased model adaptation, confusion network based decoding and confidence score estimation, pronunciation selection, language model interpolation and class based language models.