SPEECH RECOGNITION UTILIZING MULTITUDE OF SPEECH FEATURES

摘要

PROBLEM TO BE SOLVED: To provide a combination of a log-linear model with a multitude of speech features to recognize unknown speech utterances in a speech recognition system. SOLUTION: The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using the log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition. COPYRIGHT: (C)2005,JPO&NCIPI