Method and apparatus for voice enrolling an electronic computing device

Patent metadata

Field	Value
Publication number	US-9633659-B1
Application number	US-201615001315-A
Country	US
Kind code	B1
Filing date	Jan 20, 2016
Priority date	Jan 20, 2016
Publication date	Apr 25, 2017
Grant date	Apr 25, 2017

Abstract

A method and apparatus for voice enrolling an electronic computing device includes a networked server configured to receive voice data over a first communication connection from a first electronic computing device, wherein the voice data comprises a user-specific launch phrase spoken by a user. The networked server is further configured to receive an indication of a second electronic computing device to voice enroll and to initiate voice enrollment of the second electronic computing device over a second communication connection using the voice data.

First claim

We claim:

1. A method performed by a networked server, the method for transferring a voice enrollment of a first electronic computing device for use by a user to a second electronic device for use by the same user to make voice enrolling the second electronic device by directly speaking to the device unnecessary, the method comprising:
receiving voice data over a first communication connection from the first electronic computing device, wherein the voice data comprises a user-specific launch phrase spoken by the user, wherein the user-specific launch phrase spoken to the first electronic computing device is configured for training the first electronic computing device to launch in response to the user-specific launch phrase spoken by voice of the user, and wherein the voice data comprising the user-specific launch phrase is transmitted from the first electronic computing device to the server;
creating an account for the user and associating the voice data with the account of the user;
receiving an indication of a second electronic computing device to voice enroll, wherein the indication is a trigger event indicating that the second electronic computing device is to be associated with the user; and
initiating voice enrollment of the second electronic computing device over a second communication connection by sending the voice data to the second electronic computing device for use by the user for launching the second electronic computing device by speaking the launch phrase, wherein the second electronic computing device is synchronized with the voice data received from the server and associated with the user, wherein the networked server comprises a portion of a retail management system, and wherein receiving an indication of the second electronic computing device comprises receiving an order for the second electronic computing device placed from the first electronic computing device.

2. The method of claim 1 , wherein the voice enrollment of the second electronic computing device comprises voice enabling the user-specific launch phrase for a voice-activated application programmed on the second electronic computing device.

3. The method of claim 1 further comprising sending over the first communication connection to the first electronic computing device an invitation for the user to elect to have the second electronic computing device voice enrolled prior to delivery, wherein the invitation comprises a request for the voice data.

4. The method of claim 1 , wherein the networked server receives the voice data from the first electronic computing device as a data stream.

5. The method of claim 4 , further comprising encoding the voice data.

6. The method of claim 1 , wherein the networked server receives the voice data from the first electronic computing device as a data file.

7. The method of claim 1 , further comprising storing the voice data remotely from the first electronic computing device and the second electronic computing device.

8. The method of claim 1 , wherein the voice data comprises metadata specifying one or both of a capturing characteristic or an encoding characteristic of the user-specific launch phrase included in the voice data.

9. The method of claim 8 further comprising processing the voice data, using the metadata, in accordance with one or both of a hardware characteristic or a software characteristic of the second electronic computing device.

10. The method of claim 9 , wherein processing the voice data comprises transcoding the voice data from a first encoded format to a second encoded format.

11. The method of claim 9 , wherein processing the voice data comprises modifying an acoustic property of the voice data from having a first acoustic characteristic to having a second acoustic characteristic.

12. The method of claim 1 , wherein initiating voice enrollment of the second electronic computing device comprises sending the voice data over the second communication connection to the second electronic computing device, wherein the second electronic computing device is configured to use the voice data to configure itself to detect the user speaking the user-specific launch phrase.

13. The method of claim 1 , wherein initiating voice enrollment of the second electronic computing device comprises:
generating, using the voice data, a voice model for the second electronic computing device; and
sending the voice model over the second communication connection to the second electronic computing device, wherein the voice model configures the second electronic computing device to detect the user speaking the user-specific launch phrase.

14. The method of claim 1 , wherein initiating voice enrollment of the second electronic computing device comprises sending the voice data over the second communication connection to a configuring apparatus to use the voice data to configure the second electronic computing device to detect the user speaking the user-specific launch phrase.

15. The method of claim 1 , wherein the first electronic computing device and the second electronic computing device are smartphone devices.

16. A networked server comprising:
at least one communication interface configured to establish a first communication connection with a first electronic computing device and to establish a second communication connection with a second electronic computing device; and
a processing element operatively coupled to the at least one communication interface, wherein the processing element is configured to:
receive voice data over the first communication connection from the first electronic computing device, wherein the voice data comprises a user-specific launch phrase spoken by a user, wherein the user-specific launch phrase spoken to the first electronic computing device is configured for training the first electronic computing device to launch in response to the user-specific launch phrase spoken by voice of the user, and wherein the voice data comprising the user-specific launch phrase is transmitted from the first electronic computing device to the server;
create an account for the user and associate the voice data with the account of the user;
receive an indication of the second electronic computing device to voice enroll, wherein the indication is a trigger event indicating that the second electronic computing device is to be associated with the user; and
initiate voice enrollment of the second electronic computing device over the second communication connection by sending the voice data to the second electronic computing device for use by the user for launching the second electronic computing device by speaking the launch phrase, wherein the second electronic computing device is synchronized with the voice data received from the server and associated with the user, wherein the networked server comprises a portion of a retail management system, and wherein receiving an indication of the second electronic computing device comprises receiving an order for the second electronic computing device placed from the first electronic computing device.

17. The networked server of claim 16 further comprising a non-volatile storage operatively coupled to the processing element, wherein the non-volatile storage is configured to store the voice data, wherein the stored voice data is associated with the user.

18. The networked server of claim 16 further comprising an audio encoding module, implemented at least in part in hardware, operatively coupled to the processing element, wherein the audio encoding module is configured to one or both of encode or t

Assignees

• Motorola Mobility Llc

Inventors

• Agrawal Amit Kumar
• Chug Himanshu
• Rout Satyabrata

Classifications

• G10L19/173

  Transcoding, i.e. converting between two coded representations avoiding cascaded coding-decoding · CPC title

• G10L15/30 Primary

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L15/063

  Training · CPC title

• H04M2250/74

  with voice recognition means · CPC title

• G10L17/04

  Training, enrolment or model building · CPC title