COGNITIVE MODIFICATION OF SPEECH FOR TEXT-TO-SPEECH

• US 20200135173A1
• Filed: 10/31/2018
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: TRIM, Craig M., GANCI, JR., John M., BAUGHMAN, Aaron K., WYATT, Veronica
• Granted Patent: US 10,971,134 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/142 Hidden Markov Models [HMMs]

Abstract

A computer-implemented method comprising: receiving, by a computing device, an input phrase from a text generator; determining, by the computing device, a complexity level for an audience; generating, by the computing device, a plurality of target phrases including a modification of the input phrase; generating, by the computing device, respective readability scores for each of the plurality of target phrases; mapping, by the computing device, the plurality of the target phrases to the target audience complexity level to select a particular target phrase of the plurality of the target phrases; and outputting, by the computing device, the selected particular target phrase to a text-to-speech (T2S) component to cause the T2S component to output the selected particular target phrase as audible speech.

Claims

1. A computer-implemented method comprising:

receiving, by a computing device, an input phrase from a text generator;

determining, by the computing device, a complexity level for an audience;

generating, by the computing device, a plurality of target phrases including a modification of the input phrase;

generating, by the computing device, respective readability scores for each of the plurality of target phrases;

mapping, by the computing device, the plurality of the target phrases to the target audience complexity level to select a particular target phrase of the plurality of the target phrases; and

outputting, by the computing device, the selected particular target phrase to a text-to-speech (T2S) component to cause the T2S component to output the selected particular target phrase as audible speech.

2. The computer-implemented method of claim 1, wherein the text generator and the T2S component are implemented within a user device.

3. The computer-implemented method of claim 1, wherein the complexity level is determined based on a user profile associated with user identification information, wherein the user identification information is at least one selected from the group consisting of:

user name and password,

biometrics information,

facial recognition, and

voice recognition.

4. The computer-implemented method of claim 1, wherein the complexity level is determined based on user device activity.

5. The computer-implemented method of claim 1, wherein the complexity level is a lowest complexity level of respective complexity levels for each user in a group of users.

6. The computer-implemented method of claim 1, wherein the plurality of target phrases are generated using a Hidden Markov Model (HMM).

7. The computer-implemented method of claim 1, wherein the respective readability scores are generated using a Flesch-Kincaid scoring technique

8. The computer-implemented method of claim 1, wherein the input phrase originates from at least one selected from the group consisting of:

an application;

a digital assistant;

a text file;

an e-mail message;

a text message, and

a webpage.

9. The computer-implemented method of claim 1, wherein the particular target phrase is selected based on a probability of validity satisfying a threshold.

10. The computer-implemented method of claim 1, wherein a service provider at least one of creates, maintains, deploys and supports the computing device.

11. The computer-implemented method of claim 1, wherein the receiving the input phrase, the determining the complexity level, the generating the plurality of target phrases, the generating the respective readability scores, the mapping the plurality of target phrases, and the outputting the selected target phrase are provided by a service provider on a subscription, advertising, and/or fee basis.

12. The computer-implemented method of claim 1, wherein the computing device includes software provided as a service in a cloud environment.

13. The computer-implemented method of claim 1, further comprising deploying a system, wherein the deploying the system comprises providing a computer infrastructure operable to perform the receiving the input phrase, the determining the complexity level, the generating the plurality of target phrases, the generating the respective readability scores, the mapping the plurality of target phrases, and the outputting the selected target phrase.

14. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a user device to cause the user device to:

receive an input phrase from a text generator implemented within the user device;

determine a complexity level for an audience;

generate a plurality of target phrases including a modification of the input phrase;

generate respective readability scores for each of the plurality of target phrases;

map the plurality of the target phrases to the target audience complexity level to select a particular target phrase of the plurality of the target phrases; and

output the selected particular target phrase to a text-to-speech (T2S) component implemented within the user device to cause the T2S component to output the selected particular target phrase as audible speech.

15. The computer program product of claim 14, wherein the complexity level is determined based on user device activity.

16. The computer program product of claim 14, wherein the plurality of target phrases are generated using a Hidden Markov Model (HMM).

17. The computer program product of claim 14, wherein the respective readability scores are generated using a Flesch-Kincaid scoring technique.

18. The computer program product of claim 14, wherein the input phrase originates from at least one selected from the group consisting of:

an application;

a digital assistant;

a text file;

an e-mail message;

a text message, and

a webpage.

19. A system comprising:

a processor, a computer readable memory and a computer readable storage medium associated with a remote server external to a user device;

program instructions to receive an input phrase from a text generator implemented within the user device;

program instructions to determine a complexity level for an audience;

program instructions to generate a plurality of target phrases including a modification of the input phrase;

program instructions to generate respective readability scores for each of the plurality of target phrases;

program instructions to map the plurality of the target phrases to the target audience complexity level to select a particular target phrase of the plurality of the target phrases; and

program instructions to output the selected particular target phrase to a text-to-speech (T2S) component implemented within the user device to cause the T2S component to output the selected particular target phrase as audible speech,

wherein the program instructions are stored on the computer readable storage medium for execution by the processor via the computer readable memory.

20. The system of claim 19, wherein the complexity level is determined based on user device activity.