Title :
Tree-based models for speech and language
Author :
Riley, Michael D.
Author_Institution :
AT&T Bell Labs., Murray Hill, NJ, USA
Abstract :
Several applications of statistical tree-based modelling are described to problems in speech and language, including prediction of possible phonetic realizations, segment duration modelling in speech synthesis and end of sentence detection in text analysis
Keywords :
natural languages; prediction theory; speech processing; speech synthesis; statistical analysis; trees (mathematics); language; phonetic realizations; segment duration modelling; sentence end detection; speech; speech synthesis; statistical tree-based modelling; text analysis; Classification tree analysis; Entropy; Humans; Natural languages; Pattern recognition; Predictive models; Regression tree analysis; Speech analysis; Speech synthesis; Text analysis;
Conference_Titel :
Information Theory and Statistics, 1994. Proceedings., 1994 IEEE-IMS Workshop on
Conference_Location :
Alexandria, VA
Print_ISBN :
0-7803-2761-6
DOI :
10.1109/WITS.1994.513863
