Multipass ASR controlling multiple applications

摘要

A multipass processing system includes a first grammar-based speech recognition system that compares a spoken utterance to a sub-grammar. The sub-grammar includes keywords or key phrases from active grammars that each uniquely identifies one of many application engines. The first grammar-based speech recognition system generates a first grammar-based speech recognition result and a first grammar-based confidence score. A demultiplexer receives the spoken utterance through an input. The demultiplexer transmits the spoken utterance to one of many other grammar-based speech recognition systems based on the first grammar-based speech recognition-result.

主权项

1. A multipass processing system comprising:
a first grammar-based speech recognition system that compares a spoken utterance to a sub-grammar comprising keywords or key phrases from active grammars of a plurality of other grammar-based speech recognition systems and each of the keywords or key phrases uniquely identifies one of a plurality of application engines and an associated one of the plurality of other grammar-based speech recognition systems, to generate a first grammar-based speech recognition result and a first grammar-based confidence score; a demultiplexer that receives the spoken utterance through an input and transmits the spoken utterance to a selected one of the plurality of other grammar-based speech recognition systems wherein the selection of the other grammar-based speech recognition system is based on the first grammar-based speech recognition result, and wherein the selected one of the plurality of other grammar-based speech recognition systems generates a second grammar-based speech recognition result and a second confidence score; and a system management controller communicatively coupled to the plurality of other grammar-based speech recognition systems, which receives the second grammar-based speech recognition result and the second confidence score and enables forwarding of the spoken utterance from the demultiplexer to a second one of the plurality of the other grammar-based speech recognition systems in instances when the second confidence score does not exceed a predetermined threshold.