Statistical Modeling in Continuous Speech Recognition (CSR)(Invited Talk)

TL;DR

This paper reviews the development of statistical models like HMMs and N-grams in continuous speech recognition, discussing their assumptions, limitations, and ongoing research to improve system performance.

Contribution

It provides a comprehensive overview of the evolution, challenges, and future directions of statistical modeling techniques in CSR systems.

Findings

Progress in speech signal parameterisation and modeling assumptions.

Techniques to mitigate modeling assumptions' effects.

Fundamental modeling research ongoing to address limitations.

Abstract

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.