Speech-based user interface for a mobile device

• US 9,183,835 B2
• Filed: 09/27/2012
• Issued: 11/10/2015
• 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
• Primary Examiner(s): ROBERTS, SHAUN A
• Application Number:
  US13/628,657
• Publication Number:
  US 20130197915A1
• Time in Patent Office: 1,139 Days
• Field of Search: 704/244, 704/270, 704/270.1, 704/275
• US Class Current: 1/1
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 21/06 Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids G10L15/26 takes precedence
• CPC Class Codes: H04M 1/6083 by interfacing with the vehicle audio system
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00
• CPC Class Codes: H04W 92/08 between user and terminal device

Abstract

A method of providing hands-free services using a mobile device having wireless access to computer-based services includes carrying out a completed speech session via a mobile device without any physical interaction with the mobile device, wherein the speech session includes receiving a speech input from a user, and obtaining from a cloud service a service result responsive to the speech input, and providing the service result as a speech response presented to the user.

Claims

1. A method of providing hands-free services using a mobile device having wireless access to computer-based services, the method comprising carrying out a completed speech session via a mobile device without any physical interaction with the mobile device, wherein the speech session includes receiving a speech input from a user, processing the speech input into speech recognition results using an automatic speech recognition (ASR) process, identifying a primary session context from the speech recognition results, identifying an ancillary session context from the;

recognition results, obtaining service results responsive to both the primary session context and the ancillary session context identified from the speech recognition results, and providing the service results to the user.

2. The method set forth in claim 1, wherein the method further comprises carrying out the speech session using the steps of:

(a) receiving the speech input at the mobile device via a short range wireless connection;

(b) identifying a cloud service associated with the primary session context or the ancillary session context;

(c) sending a service request to the cloud service;

(d) receiving the service result from the cloud service;

(e) generating a speech response using the service result; and

(f) sending the speech response as audio speech from the mobile device via the short range wireless connection.

3. The method set forth in claim 1, further comprising sending the speech input to a remote ASR service via a wireless communication system and receiving the recognition result from the ASR service via the wireless communication system.

4. The method set forth in claim 1, further comprising the steps of:

processing the speech recognition result at the mobile device using one or more post-ASR grammars associated with different session contexts, and identifying the primary session context or ancillary session context based on the processing.

5. The method set forth in claim 2, wherein step (c) further comprises determining the service request using parameters supplied in the speech recognition result.

6. The method set forth in claim 2, wherein step (e) further comprises generating a text response and then obtaining a speech response by sending the text response to a cloud text-to-speech (TTS) service and receiving the speech response from the cloud TTS service.

7. The method set forth in claim 1, wherein the method is carried out using a vehicle having an installed vehicle audio interface, and wherein the speech session includes receiving the spoken input via the vehicle audio interface and sending the speech response to the vehicle audio interface for audible presentation in the vehicle.

8. The method set forth in claim 7, wherein the method further comprises sending the spoken input to a remote automated speech recognition (ASR) system, receiving speech recognition results from the ASR system, determining a service request from the speech recognition results, sending the service request to the cloud service, and receiving the service response from the cloud service.

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

(a) receiving speech input at a mobile device via a wireless personal area network;

(b) sending the speech input from the mobile device to an automated speech recognition (ASR) system via a wireless communication system;

(c) receiving from the ASR system speech recognition results representing at least portions of the speech input;

(d) determining a primary session context and an ancillary session context at the mobile device based on the speech recognition results;

(e) determining desired services associated with the primary session context and the ancillary session context;

(f) sending service requests to the desired services;

(g) receiving service results from the desired services;

(h) generating a speech response using the service results; and

(i) sending the speech response as audio speech from the mobile device via the wireless personal area network.

10. The method set forth in claim 9, wherein step (f) comprises sending the service requests to an application installed on the mobile device and receiving the service result from the installed application.

11. The method set forth in claim 9, wherein step (f) comprises sending the service request to a cloud service and receiving the service result from the cloud service.

12. The method set forth in claim 9, wherein step (i) comprises generating a text response based on the service result, sending the text response to a text-to-speech (TTS) service via the wireless communication system, and receiving the speech response from the TTS service via the wireless communication system.