Automatically presenting different user experiences, such as customized voices in automated communication systems

Patent metadata

Field	Value
Publication number	US-9626695-B2
Application number	US-201414451151-A
Country	US
Kind code	B2
Filing date	Aug 4, 2014
Priority date	Jun 26, 2014
Publication date	Apr 18, 2017
Grant date	Apr 18, 2017

Abstract

An automated communication system with an associated method for presenting customized voices is disclosed. The system which performs a predetermined task accepts information regarding an intended user indicating the intended user's identity, preferences, etc. Next, the system customizes one or more voices for the intended user based on the accepted information. The system then presents to the intended user one or more audible communications converted from text associated with a predetermined task performed by the system using the one or more customized voices.

First claim

The invention claimed is:

1. At least one non-transitory computer-readable medium, carrying instructions, which when executed by at least one hardware data processor, performs a method of presenting customized voices by an automated communication system, the method comprising:
accepting information regarding an intended user of the automated communication system, wherein accepting the information includes:
i) analyzing text and voice input from the user, and
ii) deducing an interaction style of the user based on the text and voice input from the user,
wherein the user's interaction style indicates a mood of the user and an interaction style that the user desires, and
wherein the mood includes being available or busy and wherein the interaction style includes a formal or an informal style, and

iii) storing data regarding the user's interaction style;

customizing or selecting one of multiple text-to-speech voices based on the accepted information,
wherein the multiple voices are audio properties of the multiple voices that vary by volume and pitch, and
wherein the multiple voices include an irreverent voice and a succinct voice; and

presenting, to the user and for audible output to the user on a computing device of the user, one or more audible communications for a task performed by the automated communication system using the one or more customized or selected voices.

2. The non-transitory computer-readable medium of claim 1 , wherein the automated communication system is a server, and wherein the task is a computerized event invitation provided by the server to the computing device of the user, a computerized greeting card provided by the server to the computing device of the user, a computerized game provided by the server to the computing device of the user, or a computerized storybook provided by the server to the computing device of the user, and wherein the server computer also provides to the user, via the computing device, a spoken advertisement.

3. The non-transitory computer-readable medium of claim 1 , further comprising
storing multiple predetermined voices,
wherein customizing or selecting the one of multiple voices includes selecting the one voice from the stored voices, and wherein the voices are each different computer-generated voices.

4. The non-transitory computer-readable medium of claim 1 , further comprising
storing multiple predetermined voice components,
wherein the customizing or selecting the one of multiple voices includes synthesizing the one voice using one or more of the stored voice components.

5. The non-transitory computer-readable medium of claim 1 , wherein
the intended user interacts with the automated communication system, and
the one or more audible communications are presented in response to inquiries from the user, and
wherein the method further comprises customizing or selecting the one or more voices based on a nature of one of the inquiries or a state of the task.

6. The non-transitory computer-readable medium of claim 1 , wherein the one voice is selected based on an occasion and an intended audience to receive the one or more audible communications, and wherein the task is an electronic invitation to attend a child's party, to attend a woman's wedding, or to attend a professor's retirement party.

7. The non-transitory computer-readable medium of claim 1 , wherein the one or more audible communications correspond to text associated with the task, wherein the task is a game that uses multiple, different voices to present different questions depending on contestants playing the game, depending on question categories, and depending on prizes involved.

8. The non-transitory computer-readable medium of claim 1 , wherein the accepted information indicates a profession or a hobby of the user.

9. The non-transitory computer-readable medium of claim 1 , further comprising:
identifying multiple stages of or roles in the task; and
assigning different customized or selected voices to the stages or roles,
wherein the presenting is performed based on a current stage of or an active role in the task.

10. A method of operating an automated communication system to present customized voices, the method comprising:
accepting information regarding an intended user of the automated communication system, wherein accepting the information includes:
i) analyzing text and voice input from the user, and
ii) deducing an interaction style of the user based on the text and voice input from the user,
wherein the user's interaction style indicates a mood of the user and an interaction style that the user desires, and
wherein the mood includes being available or busy and wherein the interaction style includes a formal or an informal style, and

iii) storing data regarding the user's interaction style;

customizing or selecting one of multiple text-to-speech voices based on the accepted information,
wherein the multiple voices are audio properties of the multiple voices that vary by volume and pitch,
wherein the customizing or selecting is performed by a hardware processor, and
wherein the multiple voices include an irreverent voice and a succinct voice; and

presenting, to the user and for audible output to the user on a computing device of the user, one or more audible communications for a task performed by the automated communication system using the one or more customized or selected voices.

11. The method of claim 10 , wherein the automated communication system is a server, and wherein the task is a computerized event invitation provided by the server to the computing device of the user, a computerized greeting card provided by the server to the computing device of the user, a computerized game provided by the server to the computing device of the user, or a computerized storybook provided by the server to the computing device of the user, and wherein the server computer also provides to the user, via the computing device, a spoken advertisement.

12. The method of claim 10 , further comprising
storing multiple predetermined voices,
wherein customizing or selecting the one of multiple voices includes selecting the one voice from the stored voices, and wherein the voices are each different computer-generated voices.

13. The method of claim 10 , further comprising
storing multiple predetermined voice components,
wherein the customizing or selecting the one of multiple voices includes synthesizing the one voice using one or more of the stored voice components.

14. The method of claim 10 , wherein
the intended user interacts with the automated communication system, and
the one or more audible communications are presented in response to inquiries from the user, and
wherein the method further comprises customizing or selecting the one or more voices based on a nature of one of the inquiries or a state of the task.

15. The method of claim 10 , wherein the one voice is selected based on an occasion and an intended audience to receive the one or more audible communications, and wherein the task is an electronic invitation to attend a child's party, to attend a woman's wedding, or to attend a professor's retirement party.

16. The method of claim 10 , wherein the one or more audible communications correspond to text associated with the task, wherein the task is a game that uses multiple, different voices to present different questions depending on contestants playing the game, depending on question categories, and depending on prizes involved.

17. The method of claim 10 , wherein the accepted information indicates a

Assignees

• Nuance Communications Inc

Inventors

• Balasubramanian Sundar
• Mcsherry Michael
• Fu Eric Jun
• Hendrick Daniel
• Katyal Deepankar
• Kay David J

Classifications

• G10L13/033

  Voice editing, e.g. manipulating the voice of the synthesiser · CPC title

• G06Q30/0255 Primary

  based on user history · CPC title

• G10L15/20

  Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence) · CPC title

• G06Q30/0267

  Wireless devices · CPC title

• G06Q30/0257

  User requested · CPC title