Devices and methods for a speech-based user interface

• US 10,720,146 B2
• Filed: 01/18/2018
• Issued: 07/21/2020
• Est. Priority Date: 05/13/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Agiomyrgiannakis, Ioannis, Henderson, Fergus James
• Primary Examiner(s): Shah, Bharatkumar S
• Application Number:
  US15/874,051
• Publication Number:
  US 20180144737A1
• Time in Patent Office: 915 Days
• Field of Search: 704258
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation
• CPC Class Codes: G10L 2021/0135 Voice conversion or morphing

Abstract

A device may identify a plurality of sources for outputs that the device is configured to provide. The plurality of sources may include at least one of a particular application in the device, an operating system of the device, a particular area within a display of the device, or a particular graphical user interface object. The device may also assign a set of distinct voices to respective sources of the plurality of sources. The device may also receive a request for speech output. The device may also select a particular source that is associated with the requested speech output. The device may also generate speech having particular voice characteristics of a particular voice assigned to the particular source.

Claims

1. A computer-implemented method comprising:

determining that a similarity between a particular set of one or more voice characteristics and another set of one or more voice characteristics associated with a different application satisfies a threshold difference;

associating, by a computing device, the particular set of one or more voice characteristics with a particular application that is installed on the computing device based on determining that the similarity between the particular set of one or more voice characteristics and the another set of one or more voice characteristics associated with the different application satisfies the threshold difference;

receiving, by the computing device, text that the particular application that is installed on the computing device has indicated is to be output as synthesized speech;

identifying, by the computing device, the particular application that provided the text from among different applications that are installed on the computing device;

selecting based on the particular application that was identified as having provided the text from among the different applications, by the computing device and from among multiple sets of one or more voice characteristics that are each pre-associated with a different one of the different applications that are installed on the computing device, the particular set of one or more voice characteristics that was associated with the particular application that is installed on the computing device and that has indicated that the text is to be output as synthesized speech, wherein the pre-associated multiple sets of one or more voice characteristics audibly distinguish for which of the different applications the speech is synthesized;

generating, by the computing device, the synthesized speech using the particular set of one or more voice characteristics that was associated with the particular application that is installed on the computing device and that has indicated that the text is to be output as synthesized speech; and

providing the synthesized speech for output.

2. The method of claim 1, wherein the particular set of one or more voice characteristics includes one or more tonality, duration, pitch, or harshness parameters.

3. The method of claim 1, comprising, before the text is received, assigning the particular set of voice characteristics to the particular application only.

4. The method of claim 3, wherein the particular set of voice characteristics is automatically assigned to the particular application.

5. The method of claim 3, wherein the particular set of voice characteristics is manually assigned to the particular application.

6. The method of claim 1, wherein the particular set of one or more voice characteristics comprises a set of one or more transforms.

7. The method of claim 1, wherein the particular set of one or more voice characteristics comprises a set of one or more voice samples.

8. The method of claim 1, wherein the particular set of one or more voice characteristics comprises a set of acoustic feature parameters.

18. The method of claim 1, wherein selecting based on the particular application that was identified as having provided the text from among the different applications, by the computing device and from among multiple sets of one or more voice characteristics that are each pre-associated with the different applications that are installed on the computing device, the particular set of one or more voice characteristics that was associated with the particular application that is installed on the computing device and that has indicated that the text is to be output as synthesized speech comprises:

selecting the particular set of one or more voice characteristics that is pre-associated with the particular application instead of another set of one or more voice characteristics that is pre-associated with another application.

19. The method of claim 1, wherein associating, by the computing device, a particular set of one or more voice characteristics with a particular application that is installed on the computing device based on determining that the similarity between the particular set of one or more voice characteristics and the another set of one or more voice characteristics associated with the different application satisfies the threshold difference is in response to determining, by the computing device, that the particular set of one or more voice characteristics are audibly distinguishable from the another set of one or more voice characteristics.

9. A non-transitory computer-readable storage device having instructions stored thereon that, when executed by a computing device, cause the computing device to perform operations comprising:

determining that a similarity between a particular set of one or more voice characteristics and another set of one or more voice characteristics associated with a different application satisfies a threshold difference;

associating, by a computing device, the particular set of one or more voice characteristics with a particular application that is installed on the computing device based on determining that the similarity between the particular set of one or more voice characteristics and the another set of one or more voice characteristics associated with the different application satisfies the threshold difference;

receiving, by the computing device, text that the particular application that is installed on the computing device has indicated is to be output as synthesized speech;

identifying, by the computing device, the particular application that provided the text from among different applications that are installed on the computing device;

selecting based on the particular application that was identified as having provided the text from among the different applications, by the computing device and from among multiple sets of one or more voice characteristics that are each pre-associated with a different one of the different applications that are installed on the computing device, the particular set of one or more voice characteristics that was associated with the particular application that is installed on the computing device and that has indicated that the text is to be output as synthesized speech, wherein the pre-associated multiple sets of one or more voice characteristics audibly distinguish for which of the different applications the speech is synthesized;

generating, by the computing device, the synthesized speech using the particular set of one or more voice characteristics that was associated with the particular application that is installed on the computing device and that has indicated that the text is to be output as synthesized speech; and

providing the synthesized speech for output.

10. The device of claim 9, wherein the particular set of one or more voice characteristics includes one or more tonality, duration, pitch, or harshness parameters.

11. The device of claim 9, the operations comprising, before the text is received, assigning the particular set of voice characteristics to the particular application only.

12. The device of claim 11, wherein the particular set of voice characteristics is automatically assigned to the particular application.

13. The device of claim 11, wherein the particular set of voice characteristics is manually assigned to the particular application.

14. The device of claim 9, wherein the particular set of one or more voice characteristics comprises a set of one or more transforms.

15. The device of claim 9, wherein the particular set of one or more voice characteristics comprises a set of one or more voice samples.

16. The device of claim 9, wherein the particular set of one or more voice characteristics comprises a set of acoustic feature parameters.

17. A system comprising:

one or more processors; and

one or more computer-readable devices including instructions that, when executed by the one or more processors, cause performance of operations including;

determining that a similarity between a particular set of one or more voice characteristics and another set of one or more voice characteristics associated with a different application satisfies a threshold difference;

associating, by a computing device, the particular set of one or more voice characteristics with a particular application that is installed on the computing device based on a determining that the similarity between the particular set of one or more voice characteristics and the another set of one or more voice characteristics associated with the different application satisfies the threshold difference;

receiving, by the computing device, text that the particular application that is installed on the computing device has indicated is to be output as synthesized speech;

identifying, by the computing device, the particular application that provided the text from among different applications that are installed on the computing device;

selecting based on the particular application that was identified as having provided the text from among the different applications, by the computing device and from among multiple sets of one or more voice characteristics that are each pre-associated with a different one of the different applications that are installed on the computing device, the particular set of one or more voice characteristics that was associated with the particular application that is installed on the computing device and that has indicated that the text is to be output as synthesized speech, wherein the pre-associated multiple sets of one or more voice characteristics audibly distinguish for which of the different applications the speech is synthesized;

generating, by the computing device, the synthesized speech using the particular set of one or more voice characteristics that was associated with the particular application that is installed on the computing device and that has indicated that the text is to be output as synthesized speech; and

providing the synthesized speech for output.