Patent Issued for Multi-Class Constrained Maximum Likelihood Linear Regression

摘要

The following quote was obtained by the news editors from the background information supplied by the inventors: "A speech recognition system determines representative text corresponding to input speech. Typically, the input speech is processed into a sequence of digital frames. Each frame can be thought of as a multi-dimensional vector that represents various characteristics of the speech signal present during a short time window of the speech. In a continuous recognition system, variable numbers of frames are organized as 'utterances' representing a period of speech followed by a pause, which in real life loosely corresponds to a spoken sentence or phrase.