Assigning and processing states and arcs of a speech recognition model in parallel processors

Abstract

A continuous, speaker independent, speech recognition method and system recognizes a variety of vocabulary input signals. A language model, which is an implicit description of a graph consisting of a plurality of states and arcs, is input into the system. An input speech signal, corresponding to a plurality of speech frames, is received and processed using a shared memory multipurpose machine having a plurality of microprocessors. Threads are created and assigned to processors, and active state subsets and active arc subsets are created and assigned to specific threads and associated microprocessors. Active state subsets and active arc subsets are processed in parallel to produce a textual representation of the speech signal. Embodiments of the invention include a two-level Viterbi search algorithm to match the input speech signals to context dependent units, an on-demand composition of finite state transducers to map context dependent units to sentences, and a determination whether a particular likelihood calculation needs to be performed or recalled from memory. The on-demand composition of finite state transducers is accomplished by multi-threading the calculation in accordance with the parallel processing feature of the system.