Handling calls on a shared speech-enabled device

• US 10,791,215 B2
• Filed: 05/16/2018
• Issued: 09/29/2020
• Est. Priority Date: 05/16/2017
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Ly, Vinh Quoc, Shah, Raunaq, Kolak, Okan, Binay, Deniz, Wang, Tianyu
• Primary Examiner(s): Deane, Jr., William J
• Application Number:
  US15/980,805
• Publication Number:
  US 20180338037A1
• Time in Patent Office: 867 Days
• Field of Search: 37920111, 37920712, 704275
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: H04L 61/4594 Address books, i.e. directories containing contact information about correspondents telephone directories in user terminals H04M1/27453
• CPC Class Codes: H04L 65/1069 Session establishment or de-establishment
• CPC Class Codes: H04L 65/1096 Supplementary features, e.g. call forwarding or call holding systems providing special services or facilities to telephony subscribers H04M3/42
• CPC Class Codes: H04M 3/42008 Systems for anonymous communication between parties, e.g. by use of disposal contact identifiers
• CPC Class Codes: H04M 3/42059 Making use of the calling party identifier

Abstract

In some implementations, an utterance that requests a voice call is received, the utterance is classified as spoken by a particular known user, the particular known user is determined to be associated with a personal voice number, and in response to determining that the particular known user is associated with a personal voice number, the voice call is initiated with the personal voice number.

Claims

1. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving, by a speech-enabled device, an utterance that requests a voice call;

classifying, by the speech-enabled device and before the voice call is initiated, the utterance as spoken by a particular known user;

providing, by the speech-enabled device and to a server, both a representation of the utterance and an indication of the particular known user that was classified as having spoken the utterance;

receiving, from the server and by the speech-enabled device, a voice number to call and an instruction to place a voice call;

determining, by the speech-enabled device and before the voice call is initiated, whether a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance, wherein the voice number used to place voice calls as the particular known user identifies the particular known user as a caller to recipients of the voice calls; and

in response to determining, by speech-enabled device and before the voice call is initiated, that a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance and receiving the instruction to place the voice call, initiating, by the speech-enabled device, the voice call to the voice number to call with the voice number used to place voice calls as the particular known user instead of with another voice number.

2. The system of claim 1, wherein classifying the utterance as spoken by a particular known user comprises:

determining whether speech in the utterance matches speech corresponding to the particular known user.

3. The system of claim 1, wherein classifying the utterance as spoken by a particular known user comprises:

determining whether a visual image of at least a portion of a speaker of the utterance matches visual information corresponding to the particular known user.

4. The system of claim 1, wherein determining whether a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance comprises:

accessing an account of the particular known user;

determining whether the account of the particular known user indicates a phone; and

determining that the phone indicated by the account of the particular known user is connected with the speech-enabled device through a local wireless connection.

5. The system of claim 4, wherein initiating the voice call comprises:

initiating the voice call through the phone connected with the speech-enabled device.

6. The system of claim 1, wherein in response to determining that a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance and receiving the instruction to place the voice call comprises:

initiating the voice call through a Voice over Internet Protocol call provider.

7. The system of claim 1, wherein determining, by the speech-enabled device, whether a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance comprises:

determining, by the speech-enabled device, that the server has provided the speech-enabled device the voice number used to place voice calls as the particular known user.

8. The system of claim 1, wherein the voice number used to place voice calls as the particular known user is also used to place calls to the particular known user.

9. The system of claim 1, wherein initiating the voice call to the voice number to call with the voice number used to place voice calls as the particular known user instead of with another voice number comprises:

identifying the voice number used to place voice calls as the particular known user; and

calling the voice number to call with the voice number used to place voice calls as the particular known user that was classified as having spoken the utterance.

10. A computer-implemented method, comprising:

receiving, by a speech-enabled device, an utterance that requests a voice call;

classifying, by the speech-enabled device and before the voice call is initiated, the utterance as spoken by a particular known user;

providing, by the speech-enabled device and to a server, both a representation of the utterance and an indication of the particular known user that was classified as having spoken the utterance;

receiving, from the server and by the speech-enabled device, a voice number to call and an instruction to place a voice call;

determining, by the speech-enabled device and before the voice call is initiated, whether a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance, wherein the voice number used to place voice calls as the particular known user identifies the particular known user as a caller to recipients of the voice calls; and

in response to determining, by speech-enabled device and before the voice call is initiated, that a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance and receiving the instruction to place the voice call, initiating, by the speech-enabled device, the voice call to the voice number to call with the voice number used to place voice calls as the particular known user instead of with another voice number.

11. The method of claim 10, wherein classifying the utterance as spoken by a particular known user comprises:

determining whether speech in the utterance matches speech corresponding to the particular known user.

12. The method of claim 10, wherein classifying the utterance as spoken by a particular known user comprises:

determining whether a visual image of at least a portion of a speaker of the utterance matches visual information corresponding to the particular known user.

13. The method of claim 10, wherein determining whether a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance comprises:

accessing an account of the particular known user;

determining whether the account of the particular known user indicates a phone; and

determining that the phone indicated by the account of the particular known user is connected with the speech-enabled device through a local wireless connection.

14. The method of claim 13, wherein initiating the voice call comprises:

initiating the voice call through the phone connected with the speech-enabled device.

15. The method of claim 10, wherein in response to determining that a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance and receiving the instruction to place the voice call comprises:

initiating the voice call through a Voice over Internet Protocol call provider.

16. The method of claim 10, wherein determining, by the speech-enabled device, whether a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance comprises:

determining, by the speech-enabled device, that the server has provided the speech-enabled device the voice number used to place voice calls as the particular known user.

17. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving, by a speech-enabled device, an utterance that requests a voice call;

classifying, by the speech-enabled device and before the voice call is initiated, the utterance as spoken by a particular known user;

providing, by the speech-enabled device and to a server, both a representation of the utterance and an indication of the particular known user that was classified as having spoken the utterance;

receiving, from the server and by the speech-enabled device, a voice number to call and an instruction to place a voice call;

determining, by the speech-enabled device and before the voice call is initiated, whether a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance, wherein the voice number used to place voice calls as the particular known user identifies the particular known user as a caller to recipients of the voice calls; and

in response to determining, by speech-enabled device and before the voice call is initiated, that a voice number used to place voice calls as the particular known user is known for the particular known user classified as having spoken the utterance and receiving the instruction to place the voice call, initiating, by the speech-enabled device, the voice call to the voice number to call with the voice number used to place voice calls as the particular known user instead of with another voice number.

18. The medium of claim 17, wherein classifying the utterance as spoken by a particular known user comprises:

determining whether speech in the utterance matches speech corresponding to the particular known user.