Statistical Modeling in Continuous Speech Recognition (CSR)(Invited Talk)
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jan-10-2013
- Country:
- North America
- United States
- Virginia > Fairfax County
- Chantilly (0.04)
- Colorado > Denver County
- Denver (0.04)
- California > San Francisco County
- San Francisco (0.04)
- Virginia > Fairfax County
- Canada > Ontario
- Toronto (0.04)
- United States
- Europe
- Greece (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.14)
- Oxfordshire > Oxford (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Hungary > Budapest
- Budapest (0.04)
- Asia
- Middle East
- Jordan (0.04)
- Republic of Türkiye > Istanbul Province
- Istanbul (0.04)
- Japan > Honshū
- Kantō > Tokyo Metropolis Prefecture > Tokyo (0.04)
- Middle East
- North America
- Genre:
- Overview (1.00)
- Research Report (0.90)
- Technology: