MULTI-DIMENSIONAL DISAMBIGUATION OF VOICE COMMANDS

PURPOSE: A multi-dimensional disambiguation of voice commands is provided to offer the result of multi-dimensional disambiguation as the selection of a user in case disambiguation between different candidate terms and actions is not automatically solved. CONSTITUTION: A server receives an audio sign...

Full description

Saved in:
Bibliographic Details
Main Authors JITKOFF JOHN NICHOLAS, BYRNE WILLIAM J, LEBEAU MICHAEL J, GRUENSTEIN ALEXANDER H
Format Patent
LanguageEnglish
Korean
Published 28.07.2011
Subjects
ACOUSTICS
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

More Information
Summary:PURPOSE: A multi-dimensional disambiguation of voice commands is provided to offer the result of multi-dimensional disambiguation as the selection of a user in case disambiguation between different candidate terms and actions is not automatically solved. CONSTITUTION: A server receives an audio signal from a client device(303). The server performs the voice recognition of the audio signal(304). The server confirms one or more possible intended actions for each candidate term(306). The server provides the candidate term and information which designates an action for the each candidate term to the display of the client device(308). The server confirms an action which a user selects(310). The server performs the selected action(312).
Bibliography:Application Number: KR20100088025