Session text-to-speech conversion

Patent metadata

Field	Value
Publication number	US-10839787-B2
Application number	US-201916392576-A
Country	US
Kind code	B2
Filing date	Apr 23, 2019
Priority date	Dec 9, 2016
Publication date	Nov 17, 2020
Grant date	Nov 17, 2020

Abstract

Examples described herein provide various devices that enable users to participate in a multiplayer session. The examples allow a user that is unable to speak, or that is incapable of speaking, to participate in an in-session voice chat by inputting text and having the text converted to speech (e.g., synthesized voice data) that can then be sent to other devices participating in the session. The user enables a text-to-speech conversion feature on his or her own device. Based on the enabled feature, functionality enabling text to be entered is activated and the entered text is converted into speech data.

First claim

The invention claimed is:

1. A method for converting text to speech within a session comprising:
determining that a feature that converts a sequence of preconfigured controller inputs to speech has been enabled for a first player using a first device to participate in the session;
receiving the sequence of preconfigured controller inputs in response to activity currently occurring in the session;
accessing a conversion model associated with a context of the activity currently occurring in the session; and
using the conversion model to convert, by one or more processing units, the sequence of preconfigured controller inputs into speech data that is to be output via other devices used by other players to participate in the session.

2. The method of claim 1 , wherein the speech data comprises one or more words that are commonly used in a title of the session.

3. The method of claim 2 , wherein the one or more words are selected from a plurality of different words based at least in part on the context of the activity currently occurring in the session.

4. The method of claim 2 , wherein the one or more words are defined by the first player.

5. The method of claim 1 , wherein the sequence of preconfigured inputs is defined by the first player.

6. The method of claim 1 , further comprising using machine learning techniques to update the conversion model.

7. The method of claim 1 , wherein the feature is enabled using an operating system component called upon, via an application programming interface, by program code of a title of the session to provide voice communications during the session.

8. The method of claim 1 , wherein the feature indicates whether synthesized voice communications comprise a female synthesized voice or a male synthesized voice.

9. A device for converting text to speech within a session, the device comprising:
one or more processing units; and
a computer-readable medium having encoded thereon computer-executable instructions to configure the one or more processing units to:
determine that a feature that converts a sequence of preconfigured controller user inputs to speech has been enabled for a first player using a first device to participate in the session;
receive the sequence of preconfigured controller user inputs in response to activity currently occurring in the session;
access a conversion model associated with a context of the activity currently occurring in the session; and
use the conversion model to convert the sequence of preconfigured controller user inputs into speech data that is to be output via other devices used by other players to participate in the session.

10. The device of claim 9 , wherein the speech data comprises one or more words that are commonly used in a title of the session.

11. The device of claim 10 , wherein the one or more words are selected from a plurality of different words based at least in part on the context of the activity currently occurring in the session.

12. The device of claim 10 , wherein the one or more words are defined by the first player.

13. The device of claim 9 , wherein the sequence of preconfigured user inputs is defined by the first player.

14. The device of claim 9 , wherein the computer-executable instructions further configure the one or more processing units to use machine learning techniques to update the conversion model.

15. The device of claim 9 , wherein the feature is enabled using an operating system component called upon, via an application programming interface, by program code of a title of the session to provide voice communications during the session.

16. The device of claim 9 , wherein the feature indicates whether synthesized voice communications comprise a female synthesized voice or a male synthesized voice.

17. A system for converting text to speech within a session, the system comprising:
one or more processing units; and
a computer-readable medium having encoded thereon computer-executable instructions to configure the one or more processing units to:
receive data indicating that a feature that converts a sequence of preconfigured controller inputs to speech has been enabled for a first player using a first device to participate in the session;
receive, from the first device, the sequence of preconfigured controller inputs that captures responses to activity currently occurring in the session;
access a conversion model that includes a library of utterances associated with a context of the activity currently occurring in the session;
use the conversion model to convert the sequence of preconfigured controller inputs into speech data; and
send the speech data to at least one of the first device or other devices used by other players to participate in the session.

18. The system of claim 17 , wherein the speech data comprises one or more words that are selected based at least in part on the context of the activity currently occurring in the session.

19. The system of claim 17 , wherein the sequence of preconfigured inputs is defined by the first player.

20. The system of claim 17 , wherein the feature is enabled using an operating system component called upon, via an application programming interface, by program code of a title of the session to provide voice communications during the session.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Kepner Jason
• Thomas Evelyn R
• Ruzyski David
• Dewey Jeremy L
• Hall Martin
• Mccammon Joshua R
• Giscombe Stephen E
• Cooper Thomas
• Ludwig Dana

Classifications

• G10L13/033

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

• H04L51/046

  Interoperability with other network applications or services · CPC title

• G10L13/00

  Speech synthesis; Text to speech systems · CPC title

• A63F13/87

  Communicating with other players during game play, e.g. by e-mail or chat · CPC title

• A63F13/533

  for prompting the player, e.g. by displaying a game menu · CPC title