Recognition of Continuous Speech: Segmentation and Classification using Signature Table Adaptation. AIM-213
- Thosar, Ravindra B.
- This report explores the possibility of using a set of features for segmentation
- and recognition of continuous speech. The features are not necessarily
- "distinctive" or minimal, in the sense that they do not divide the phonemes
- into mutually exclusive subsets, and can have high redundancy. This concept of
- feature can thus avoid apriori binding between the phoneme categories to be
- recognized and the set of features defined in a particular system.
- An adaptive technique is used to find the probability of the presence of a
- feature. Each feature is treated independently of other features. An unknown
- utterance is thus represented by a feature graph with associated probabilities.
- It is hoped that such a representation would be valuable for a hypothesize-test
- paradigm as opposed to a one which operates on a linear symbolic input.
- Stanford Artificial Intelligence Laboratory
- Memo (Stanford Artificial Intelligence Laboratory)
- Artificial intelligence
- Finding Aid
- Stanford Artificial Intelligence Laboratory Records (SC1041)
- Stanford University. Libraries. Department of Special Collections and University Archives
- Use and reproduction:
- The materials are open for research use and may be used freely for non-commercial purposes with an attribution. For commercial permission requests, please contact the Stanford University Archives (email@example.com).
- Copyright © The Board of Trustees of the Leland Stanford Junior University. All rights reserved.