Distributed hardware sharing for speech processing
First Claim
1. A method for operating a multistation intercommunication system, wherein speech processing is executed on at least two respective levels of generic complexity with respect to speech receivable on multiple parallel stations coexistently, characterized in that said method comprises the steps of:
- receiving human speech in one or more origin stations and detecting a necessity for understanding such speech in an associated application environment;
controlling the actual intercommunication in a distributed manner, by detecting temporal speech items to be recognized and automatically dynamically assigning the speech items instantaneously to one or more of a plurality of distributed speech recognizing facilities to eventually generate recognized items;
further controlling the actual communication to understand the recognized items in a context of the application in question through assigning the recognized items to one or more of a plurality of speech understanding facilities to generate newly understood speech items that have been understood;
wherein said dynamically assigning step further comprises assigning to an instantaneously determined best suited speech recognizing facility in a distributed manner and based on a combination of contingency and statistical measures.
8 Assignments
0 Petitions
Accused Products
Abstract
In a multistation intercommunication system human speech is processed on at least two respective levels of generic complexity. The speech is received in one or more origin stations in parallel and a necessity is detected to understand the speech in an associated application environment. Intercommunication is controlled in a distributed manner, by detecting temporal speech items to be recognized and dynamically assigning speech items amongst one or more of a plurality of distributed speech recognizing facilities to eventually generate recognized items. Further intercommunication is controlled to understand recognized items in a further context of the application in question through assigning the recognized items amongst one or more of a plurality of speech understanding facilities to generate speech items that have been understood. Assigning is effected in a distributed manner as based on a combination of contingency and statistics.
142 Citations
5 Claims
-
1. A method for operating a multistation intercommunication system, wherein speech processing is executed on at least two respective levels of generic complexity with respect to speech receivable on multiple parallel stations coexistently, characterized in that said method comprises the steps of:
-
receiving human speech in one or more origin stations and detecting a necessity for understanding such speech in an associated application environment;
controlling the actual intercommunication in a distributed manner, by detecting temporal speech items to be recognized and automatically dynamically assigning the speech items instantaneously to one or more of a plurality of distributed speech recognizing facilities to eventually generate recognized items;
further controlling the actual communication to understand the recognized items in a context of the application in question through assigning the recognized items to one or more of a plurality of speech understanding facilities to generate newly understood speech items that have been understood;
wherein said dynamically assigning step further comprises assigning to an instantaneously determined best suited speech recognizing facility in a distributed manner and based on a combination of contingency and statistical measures. - View Dependent Claims (2, 3, 4, 5)
-
Specification