SERVICES IDENTIFICATION AND INITIATION FOR A SPEECH-BASED INTERFACE TO A MOBILE DEVICE

• US 20130197907A1
• Filed: 09/27/2012
• Published: 08/01/2013
• Est. Priority Date: 10/18/2011
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Burke, Denis R., Gurovich, Danilo, Rudman, Daniel E., Fry, Keith A., McCutchen, Shane M., Carnevale, Marco T., Gupta, Mukesh
• Granted Patent: US 9,159,322 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method of providing hands-free services using a mobile device having wireless access to computer-based services includes establishing a short range wireless connection between a mobile device and one or more audio devices that include at least a microphone and speaker; receiving at the mobile device speech inputted via the microphone from a user and sent via the short range wireless connection; wirelessly transmitting the speech input from the mobile device to a speech recognition server that provides automated speech recognition (ASR); receiving at the mobile device a speech recognition result representing the content of the speech input; determining a desired service by processing the speech recognition result using a first, service-identifying grammar; determining a user service request by processing at least some of the speech recognition result using a second, service-specific grammar associated with the desired service; initiating the user service request and receiving a service response; generating an audio message from the service response; and presenting the audio message to the user via the speaker.

Claims

1. A method of providing hands-free services using a mobile device having wireless access to computer-based services, comprising the steps of:

(a) establishing a short range wireless connection between a mobile device and one or more audio devices that include at least a microphone and speaker;

(b) receiving at the mobile device speech inputted via the microphone from a user and sent via the short range wireless connection;

(c) wirelessly transmitting the speech input from the mobile device to a speech recognition server that provides automated speech recognition (ASR);

(d) receiving at the mobile device a speech recognition result representing the content of the speech input;

(e) determining a desired service by processing the speech recognition result using a first, service-identifying grammar;

(f) determining a user service request by processing at least some of the speech recognition result using a second, service-specific grammar associated with the desired service;

(g) initiating the user service request and receiving a service response;

(h) generating an audio message from the service response; and

(i) presenting the audio message to the user via the speaker.

2. The method set forth in claim 1, wherein the ASR server comprises a generalized third party cloud service and wherein step (c) further comprises sending the speech input to the generalized third party cloud service.

3. The method set forth in claim 2, wherein step (d) further comprises receiving the speech recognition result prior to determining a session context and wherein step (e) further comprises determining the session context using the first grammar.

4. The method set forth in claim 1, wherein the first, service-identifying grammar includes vocabulary indicative of a plurality of session contexts, and wherein step (e) comprises determining from the speech recognition result and the first grammar which one or more of the session contexts relates to the content of the speech input.

5. The method set forth in claim 4, wherein the session contexts include dining, weather, traffic, navigation, scheduling, and messaging.

6. The method set forth in claim 4, wherein step (e) further comprises identifying both a primary session context and one or more ancillary session contexts.

7. The method set forth in claim 6, wherein step (e) further comprises determining a desired service associated with the primary session context and an ancillary service for each of the ancillary session contexts.

8. The method set forth claim 1, wherein the method is carried out using a vehicle having an installed audio user interface, wherein step (a) further comprises establishing the short range wireless connection between the mobile device and audio user interface, and wherein step (i) further comprises sending the audio message to the audio user interface via the short range wireless connection for audible presentation in the vehicle.

9. The method set forth claim 1, wherein step (g) comprises sending the service request to an application installed on the mobile device and receiving the service response from the installed application.

10. The method set forth claim 1, wherein step (g) comprises sending the service request to a cloud service and receiving the service response from the cloud service.

11. The method set forth claim 1, wherein step (h) comprises generating a text response based on the service response, sending the text response to a cloud text-to-speech (TTS) service via a wireless communication system, and receiving the audio message from the TTS service via the wireless communication system.