Applications of stochastic context-free grammars using the Inside-Outside algorithm

This paper describes two applications in speech recognition of the use of stochastic context-free grammars (SCFGs) trained automatically via the Inside-Outside Algorithm. First, SCFGs are used to model VQ encoded speech for isolated word recognition and are compared directly to HMMs used for the same task. It is shown that SCFGs can model this low-level VQ data accurately and that a regular grammar based pre-training algorithm is effective both for reducing training time and obtaining robust solutions. Second, an SCFG is inferred from a transcription of the speech used to train a phoneme-based recognizer in an attempt to model phonotactic constraints. When used as a language model, this SCFG gives improved performance over a comparable regular grammar or bigram. © 1991.

Measurement of the unburnt gas temperature in an IC engine by means of a pressure transducer

A novel method of measuring cylinder gas temperature in an internal combustion engine cylinder is introduced. The physical basis for the technique is that the flow rate through an orifice is a function of the temperature of the gas flowing through the orifice. Using a pressure transducer in the cylinder, and another in a chamber connected to the cylinder via an orifice, it is shown how the cylinder temperature can be determined with useful sensitivity. In this paper the governing equations are derived, which show that the heat transfer characteristics of the chamber are critical to the performance of the system, and that isothermal or adiabatic conditions give the optimum performance. For a typical internal combustion engine, it is found that the pre-compression cylinder temperature is related to the chamber pressure late in the compression process with sensitivity of the order of 0.005 bar/K. Copyright © 2010 SAE International.