Statistical Modeling in Continuous Speech Recognition (CSR)(Invited Talk)
This is an incremental review paper for researchers and practitioners in speech recognition, summarizing existing methods and current challenges.
The paper reviews the evolution of statistical modeling techniques like hidden Markov models and N-grams in continuous speech recognition, highlighting their role in enabling real-world applications such as large vocabulary transcription and interactive dialogues, while noting ongoing limitations and fundamental research.
Automatic continuous speech recognition (CSR) is sufficiently mature that a variety of real world applications are now possible including large vocabulary transcription and interactive spoken dialogues. This paper reviews the evolution of the statistical modelling techniques which underlie current-day systems, specifically hidden Markov models (HMMs) and N-grams. Starting from a description of the speech signal and its parameterisation, the various modelling assumptions and their consequences are discussed. It then describes various techniques by which the effects of these assumptions can be mitigated. Despite the progress that has been made, the limitations of current modelling techniques are still evident. The paper therefore concludes with a brief review of some of the more fundamental modelling work now in progress.