Abstract
A crucial issue in triphone-based continuous-speech recognition is the large number of parameters to be estimated against the limited availability of training data. This problem can be relieved by composing a triphone model from less context-dependent models. This paper introduces a new statistical framework, derived from Bayesian statistics, to perform such a composition. The potential power of this new framework is explored, both algorithmically and experimentally, by an implementation with hidden Markov modelling techniques. In particular, we describe an implementation based on the mixture-Gaussian hidden Markov models (HMMs) incorporating state-level parameter tying. This implemented model is applied to the recognition of the 39-phone set on the TIMIT database, achieving 74.4% and 75.6% accurate, respectively, on the core and complete test sets.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
