BOLTZMANN MACHINES FOR SPEECH RECOGNITION.

Boltzmann machines offer a new and exciting approach to automatic speech recognition, and provide a rigorous mathematical formalism for parallel computing arrays. In this paper we briefly summarize Boltzmann machine theory, and present results showing their ability to recognize both static and time-varying speech patterns. A machine with 2000 units was able to distinguish between the 11 steady-state vowels in English with an accuracy of 85%. The stability of the learning algorithm and methods of preprocessing and coding speech data before feeding it to the machine are also discussed. A new type of unit called a carry input unit, which involves a type of state-feedback, was developed for the processing of time-varying patterns and this was tested on a few short sentences. Use is made of the implications of recent work into associative memory, and the modelling of neural arrays to suggest a good configuration of Boltzmann machines for this sort of pattern recognition.

Analysis and performance assessment of 6-pulse inverter-fed 3-phase and 6-phase induction machines

The paper describes a model for a 6-phase induction motor driven by an inverter operating in a 6-pulse (square wave) mode. The model is implemented and performance, in terms of torque, current, efficiency and pulsating torque, compared to the performance of a 3-phase motor (both sine and 6-pulse supplied). The models are verified experimentally, in particular the efficiency performance, and it is illustrated that the improvement in inverter efficiency when in 6-pulse operating mode may improve the performance of the overall system. © 2005 IEEE.