Speech recognition manager
First Claim
1. A speech recognition manager for a processing system operating in accordance with one or more application programs responsive to input commands, said manager receiving representations of one or more words from an acoustic processor that is responsive to sound to generate said word representations, said manager comprising:
- a memory for storing data for a plurality of context states;
means for determining one context state as a current context state; and
means responsive to said data stored in said memory for the one context state determined to be current for assigning to a word representation received from said acoustic processor a first meaning represented by a first input command when said current context state is determined to be a first context state and a second meaning represented by a second input command when said current context state is determined to be a second context state.
6 Assignments
0 Petitions
Accused Products
Abstract
A speech recognition manager receives representations of one or more words from a speech decoding system and interprets the received words based upon the current context state so as to provide extremely accurate, flexible, extendable and scalable speech recognition and interpretation. The speech recognition manager limits the number of words that the speech decoding system can recognize in a given context state in order to increase the speed and accuracy of the speech recognition process. Whenever the context state changes, the manager loads a new list of words that can be recognized for the new context state into the speech decoding system so that while the speed and accuracy of the speech recognition process is increased, the total grammatical structure recognized can be easily increased as well.
370 Citations
40 Claims
-
1. A speech recognition manager for a processing system operating in accordance with one or more application programs responsive to input commands, said manager receiving representations of one or more words from an acoustic processor that is responsive to sound to generate said word representations, said manager comprising:
-
a memory for storing data for a plurality of context states; means for determining one context state as a current context state; and means responsive to said data stored in said memory for the one context state determined to be current for assigning to a word representation received from said acoustic processor a first meaning represented by a first input command when said current context state is determined to be a first context state and a second meaning represented by a second input command when said current context state is determined to be a second context state. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A speech recognition manager for a processing system operating in accordance with one or more application programs responsive to input commands, said manager receiving representations of one or more words from an acoustic processor that is responsive to sound to generate said word representations using a data file that limits the word representations that can be generated, said manager comprising:
-
a memory for storing, for each of a plurality of context states, a data file that limits the word representations that can be generated for the context state and a meaning file that correlates word representations to input commands for the context state, at least one of said input commands being a context state transition input command; means for determining one context state as the current context state; means responsive to said meaning file for the determined current context state for assigning to a word representation received from said acoustic processor a first meaning represented by a first input command, said determining means being responsive to a context state transition input command to determine a new current context state. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16, 17)
-
-
18. A system responsive to spoken utterances for carrying out actions, comprising:
-
a microphone to pick up speech; a speech decoding system for generating word representations from speech; a speech recognition manager for converting word representations received from said speech decoding system to input commands based upon one context state determined to be current at the time of receipt of a word representation by the speech recognition manager; and a processing system operating in accordance with one or more applications responsive to input commands from said speech recognition manager for implementing actions associated with said input commands wherein different actions are implemented in response to different input commands. - View Dependent Claims (19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40)
-
Specification