HYBRID COMMAND AND CONTROL BETWEEN RESIDENT AND REMOTE SPEECH RECOGNITION FACILITIES IN A MOBILE VOICE-TO-SPEECH APPLICATION

• US 20110054900A1
• Filed: 08/27/2010
• Published: 03/03/2011
• Est. Priority Date: 03/07/2007
• Status: Abandoned Application

• Current Assignee: Vlingo Corporation (Microsoft Corporation)
• Original Assignee: Vlingo Corporation (Microsoft Corporation)
• Inventors: Phillips, Michael S., Nguyen, John N.
• Application Number:
  US12/870,453
• Publication Number:
  US 20110054900A1
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

In embodiments of the present invention improved capabilities are described for hybrid command and control between resident and remote speech recognition facilities in controlling a mobile communication facility comprising accepting speech presented by a user using a resident capture facility on the mobile communication facility while the user engages an interface that enables a command mode for the mobile communications facility; processing the speech using a resident speech recognition facility to recognize command elements and content elements; transmitting at least a portion of the speech through a wireless communication facility to a remote speech recognition facility; transmitting information from the mobile communication facility to the remote speech recognition facility, wherein the information includes information about a command recognizable by the resident speech recognition facility; generating speech-to-text results utilizing a hybrid of the resident speech recognition facility and the remote speech recognition facility based at least in part on the speech and on the information related to the mobile communication facility; and transmitting the text results for use on the mobile communications facility.

Claims

1. A method of controlling a mobile communication facility comprising:

accepting speech presented by a user using a resident capture facility on the mobile communication facility while the user engages an interface that enables a command mode for the mobile communications facility;

processing the speech using a resident speech recognition facility to recognize command elements and content elements;

transmitting at least a portion of the speech through a wireless communication facility to a remote speech recognition facility;

transmitting information from the mobile communication facility to the remote speech recognition facility, wherein the information includes information about a command recognizable by the resident speech recognition facility;

generating speech-to-text results utilizing a hybrid of the resident speech recognition facility and the remote speech recognition facility based at least in part on the speech and on the information related to the mobile communication facility; and

transmitting the text results for use on the mobile communications facility.

2. The method of claim 1, further comprising executing an action on the mobile communication facility based on the results of the resident speech recognition facility and remote speech recognition facility.

3. The method of claim 2, wherein the action may include at least one of placing a phone call, executing a web search, finding a business, sending a text message, and sending an email.