Competitive training in hidden Markov models

The use of hidden Markov models is placed in a connectionist framework, and an alternative approach to improving their ability to discriminate between classes is described. Using a network style of training, a measure of discrimination based on the a posteriori probability of state occupation is proposed, and the theory for its optimization using error back-propagation and gradient ascent is presented. The method is shown to be numerically well behaved, and results are presented which demonstrate that when using a simple threshold test on the probability of state occupation, the proposed optimization scheme leads to improved recognition performance.

MMI training for continuous phoneme recognition on the TIMIT database

This paper reports our experiences with a phoneme recognition system for the TIMIT database which uses multiple mixture continuous density monophone HMMs trained using MMI. A comprehensive set of results are presented comparing the ML and MMI training criteria for both diagonal and full covariance models. These results using simple monophone HMMs show clear performance gains achieved by MMI training, and are comparable to the best reported by others including those which use context-dependent models. In addition, the paper discusses a number of performance and implementation issues which are crucial to successful MMI training.

Addressing the cognitive and social influence inhibitors during the ideation stages of technology roadmapping workshops

Technology roadmapping workshops are essentially a social mechanism for exploring, creating, shaping and implementing ideas. The front-end of a roadmapping session is based on brainstorming in order to tap into the group's diverse knowledge. The aim of this idea stimulation activity is to capture and share as many perspectives as possible across the full scope of the area of interest. The premise to such group brainstorming is that the sharing and exchange of ideas leads to cognitive stimulation resulting in a greater overall group idea generation performance in terms of the number, variety and originality of ideas. However, it must be recognized that the ideation stage in a roadmapping workshop is a complex psychosocial phenomenon with underlying cognitive and social processes. Thus, there are downsides to group interactions and these must be addressed in order to fully benefit from the power of a roadmapping workshop. This paper will highlight and discuss the key cognitive and social inhibitors involved. These include: production blocking, evaluation apprehension, free riding/social loafing, low norm setting/matching. Facilitation actions and process adjustments to counter such negative factors will be identified so as to provide a psychosocial basis for improving the running of roadmapping workshops. © 2009 PICMET.

Foot contact detection for sprint training

We introduce a new algorithm to automatically identify the time and pixel location of foot contact events in high speed video of sprinters. We use this information to autonomously synchronise and overlay multiple recorded performances to provide feedback to athletes and coaches during their training sessions. The algorithm exploits the variation in speed of different parts of the body during sprinting. We use an array of foreground accumulators to identify short-term static pixels and a temporal analysis of the associated static regions to identify foot contacts. We evaluated the technique using 13 videos of three sprinters. It successfully identifed 55 of the 56 contacts, with a mean localisation error of 1.39±1.05 pixels. Some videos were also seen to produce additional, spurious contacts. We present heuristics to help identify the true contacts. © 2011 Springer-Verlag Berlin Heidelberg.