The HTK HMM Toolkit

Phil Woodland, Gunnar Evermann, Steve Young

HTK is a portable toolkit for building and manipulating hidden Markov models. HTK is primarily used for speech recognition research although it has been used for numerous other applications including research into speech synthesis, handwriting recognition and DNA sequencing. HTK is in use at hundreds of sites worldwide. It is now available for free download.

HTK consists of a set of library modules and tools available in C source form. The tools provide sophisticated facilities for speech analysis, HMM training, testing and results analysis. The software supports HMMs using both continuous density mixture Gaussians and discrete distributions and can be used to build complex HMM systems. The HTK release contains extensive documentation and examples.

HTK was originally developed at CUED by Steve Young and Phil Woodland and it has been used as a basis for CUED's HMM-based large vocabulary speech recognition systems. In 1993 Entropic Research Laboratory Inc. acquired the rights to sell HTK and the development of HTK was fully transferred to Entropic in 1995 when the Entropic Cambridge Research Laboratory Ltd was established. HTK was sold by Entropic until 1999 when Microsoft bought Entropic. Microsoft has now licensed HTK back to CUED and is providing support so that CUED can distribute HTK and provide development support via the HTK3 web site.

The initial HTK3 release is closely based on the final Entropic release, but in future we are intending to integrate into HTK3 a number of the features that have been used at CUED in research systems and provide infrastructure for speech recognition research such as word lattices for standard tasks.
Last modified: Tue Sep 26 19:30:25 BST 2000