A method for noise-robust context-aware pattern discovery and recognition from categorical sequences

An efficient method for weakly supervised pattern discovery and recognition from discrete categorical sequences is introduced. The method utilizes two parallel sources of data: categorical sequences carrying some temporal or spatial information and a set of labeled, but not exactly aligned, contextual events related to the sequences. From these inputs the method builds associative models able to describe systematically co-occurring structures in the input streams. The learned models, based on transitional probabilities of events observed at several different time lags, inherently segment and classify novel sequences into contextual categories. Learning and recognition processes are purely incremental and computationally cheap, making the approach suitable for on-line learning tasks. The capabilities of the algorithm are demonstrated in a keyword learning task from continuous infant-directed speech and a continuous speech recognition task operating at varying noise levels.

► Learning of temporally distributed and a priori unknown patterns without exact temporally aligned annotation.
► Modeling of long-range dependencies in sequential data without making the Markov assumption.
► Computationally fast and incremental one-pass learning and recognition.