Future Plans

In the short-term we are intending to integrate into HTK3 a number of the features that have been used at CUED in research systems. These include PLP analysis, side-based cepstral mean and variance normalisation. In the longer term more advanced facilities developed at CUED will be integrated in the released code base.

We also hope to provide more speech recognition infrastructure in a form that can be used with HTK. This will include for example word lattices for standard speech recognition tasks along with some lattice manipulation facilities.

In the medium term we also hope to make available a capable large vocabulary decoder that provides an efficient route to generate and re-score word lattices with cross-word context-dependent HMMs and long-span N-grams.

If you'd like to provide help with any of the above tasks, please contact us either by posting to the HTK-developers mailing list or emailing us privately at htk-mgr@eng.cam.ac.uk.