6 April 1995 Word spotting with the gamma neural model
Author Affiliations +
This paper discusses the application of the gamma neural model to word spotting. The gamma model is a dynamic neural model where the conventional tap delay line of the TDNN is replaced by a local recursive memory structure. This model is able to find the best memory depth for a given processing task when the number of taps in the memory is specified. It can also compensate for time warping. In our approach, word spotting is the detection of a signature (the keyword under analysis) in a noisy background (other words of continuous speech). Unlike other approaches, we do not segment the input, and the neural net learns over time how to recognize the patterns associated with a given word. We test two gamma model topologies for their sensitivity to time warping and amplitude variations.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Craig Fancourt, Craig Fancourt, Neil Euliano, Neil Euliano, Jose C. Principe, Jose C. Principe, } "Word spotting with the gamma neural model", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); doi: 10.1117/12.205183; https://doi.org/10.1117/12.205183


Back to Top