In Continuous Speech Recognition (CSR) systems, acoustic and Language Models (LM) must be integrated. To get optimum CSR performances, it is well-known that heuristic factors must ...
This paper investigates the problem of incorporating auxiliary information (e.g. pitch) for speech recognition using dynamic Bayesian networks (DBNs). Previous works usually model...
Abstract A framework for dialectal Chinese speech recognition is proposed and studied, in which a relatively small dialectal Chinese (or in other words Chinese influenced by the na...
Jing Li, Thomas Zheng, William Byrne, Daniel Juraf...
The key problem to be faced when building a HMM-based continuous speech recogniser is maintaining the balance between model complexity and available training data. For large vocab...
Statistical language models play a major role in current speech recognition systems. Most of these models have focussed on relatively local interactions between words. Recently, h...