Segment Boundary Detection via Class Entropy Measurements in Connectionist Phoneme Recognition
This is an incremental improvement for speech processing, specifically in phoneme recognition, by proposing a simple entropy-based method for boundary detection.
The paper tackled the problem of detecting phonetic segment boundaries by using class entropy from a connectionist phoneme recognizer, achieving precision and recall measured as ratios of predicted boundaries within 10 or 20 msec of reference boundaries.
This article investigates the possibility to use the class entropy of the output of a connectionist phoneme recogniser to predict time boundaries between phonetic classes. The rationale is that the value of the entropy should increase in proximity of a transition between two segments that are well modelled (known) by the recognition network since it is a measure of uncertainty. The advantage of this measure is its simplicity as the posterior probabilities of each class are available in connectionist phoneme recognition. The entropy and a number of measures based on differentiation of the entropy are used in isolation and in combination. The decision methods for predicting the boundaries range from simple thresholds to neural network based procedure. The different methods are compared with respect to their precision, measured in terms of the ratio between the number C of predicted boundaries within 10 or 20 msec of the reference and the total number of predicted boundaries, and recall, measured as the ratio between C and the total number of reference boundaries.