Multiple speech recognition engines
First Claim
1. A system comprising:
- a plurality of available speech recognition engines configured to interpret spoken input, if selected as a chosen speech recognition engine;
a user interface configured to receive the spoken input; and
a speech recognition engine manager configured to;
dynamically build heuristics relating to a quantity of misrecognitions of past spoken input of a particular user over time by the available speech recognition engines,track user preference information over time relating to a preferred speech recognition engine of the particular user for use in an application; and
select, based on the dynamically built heuristics, the tracked user preference information, and further based on receiving spoken input via the user interface, the chosen speech recognition engine from amongst the available speech recognition engines.
2 Assignments
0 Petitions
Accused Products
Abstract
A system having multiple speech recognition engines, each operable to recognize spoken data, is described. A speech recognition engine manager detects the speech recognition engines, and selects at least one for recognizing spoken input from a user, via a user interface. In this way, a speech recognition engine that is particularly suited to a current environment may be selected. For example, a speech recognition engine that is particularly suited for, or preferred by, the user may be selected, or a speech recognition engine that is particularly suited for a particular type of interface, interface element, or application, may be selected. Multiple ones of the speech recognition engines may be selected and simultaneously maintained in an active state, by maintaining a session associated with each of the engines. Accordingly, users'"'"' experience with voice applications may be enhanced, and, in particular, users with physical disabilities may more easily interact with software applications.
61 Citations
17 Claims
-
1. A system comprising:
-
a plurality of available speech recognition engines configured to interpret spoken input, if selected as a chosen speech recognition engine; a user interface configured to receive the spoken input; and a speech recognition engine manager configured to; dynamically build heuristics relating to a quantity of misrecognitions of past spoken input of a particular user over time by the available speech recognition engines, track user preference information over time relating to a preferred speech recognition engine of the particular user for use in an application; and select, based on the dynamically built heuristics, the tracked user preference information, and further based on receiving spoken input via the user interface, the chosen speech recognition engine from amongst the available speech recognition engines. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A computer-implemented method comprising:
- determining available speech recognition engines;
dynamically building heuristics relating to a quantity of misrecognitions of past spoken input of a particular user over time by the available speech recognition engines; tracking user preference information over time relating to a preferred speech recognition engine of the particular user for use in an application; receiving spoken input via a user interface; selecting, based on the dynamically built heuristics, the tracked user preference information, and further based on receiving spoken input via the user interface, a chosen recognition engine from amongst the available speech recognition engines; and interpreting the spoken input using the chosen speech recognition engine. - View Dependent Claims (10, 11, 12, 13)
- determining available speech recognition engines;
-
14. A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to:
-
determine available speech recognition engines; dynamically build heuristics relating to a quantity of misrecognitions of past spoken input of a particular user over time by the available speech recognition engines; track user preference information over time relating to a preferred speech recognition engine of the particular user for use in an application; receive spoken input via a user interface; select, based on the dynamically built heuristics, the tracked user preference information, and further based on receiving spoken input via the user interface, a chosen speech recognition engine from amongst the available speech recognition engines; and interpret the spoken input using the chosen speech recognition engine. - View Dependent Claims (15, 16, 17)
-
Specification