Systems and methods for correcting text-to-speech pronunciation

• US 9,972,301 B2
• Filed: 10/18/2016
• Issued: 05/15/2018
• Est. Priority Date: 10/18/2016
• Status: Active Grant

• Current Assignee: Mastercard International Incorporated (MasterCard Incorporated)
• Original Assignee: Mastercard International Incorporated (MasterCard Incorporated)
• Inventors: Lacoss-Arnold, Jason Jay
• Primary Examiner(s): COLUCCI, MICHAEL C
• Application Number:
  US15/296,888
• Publication Number:
  US 20180108344A1
• Time in Patent Office: 574 Days
• Field of Search: 704200, 704243, 704 2, 704260, 345473, 348157
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G10L 13/047 Architecture of speech synthesisers
• 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 13/10 Prosody rules derived from text; Stress or intonation

Abstract

A text-to-speech (TTS) computing includes a processor and a memory. The TTS computing device is configured to generate a machine pronunciation of a text data according to at least one phonetic rule, and provide the machine pronunciation to a user interface of the TTS computing device such that the machine pronunciation is audibly communicated to a user of the TTS computing device. The TTS computing device is also configured to receive a pronunciation correction of the machine pronunciation from the user via the user interface, and store the pronunciation correction in a TTS data source. The TTS computing device is further configured to assign the pronunciation correction provided by the user to a user profile that corresponds to the text data.

Claims

1. A text-to-speech (TTS) computing device comprising one or more processors in communication with one or more memory devices, the TTS computing device configured to:

generate a machine pronunciation of a text data according to at least one phonetic rule;

provide the machine pronunciation to a user interface of the TTS computing device such that the machine pronunciation is audibly communicated to a user of the TTS computing device;

receive a pronunciation correction of the machine pronunciation from the user via the user interface;

determine a first geographic location indicating where the pronunciation correction was provided by the user to the user interface;

store the pronunciation correction and the first geographic location in a TTS data source;

assign the pronunciation correction provided by the user to a user profile that corresponds to the text data;

determine a second geographic location indicating where the TTS computing device is currently located;

provide, to the user interface, the machine pronunciation if the second geographic location is outside of a predetermined distance of the first geographic location; and

provide, to the user interface, an updated machine pronunciation based on the pronunciation correction if the second geographic location is within the predetermined distance of the first geographic location.

2. The TTS computing device of claim 1, wherein said TTS computing device if further configured to translate the pronunciation correction received from the user from audio data to an updated text data for use in generating the machine pronunciation.

3. The TTS computing device of claim 1, wherein said TTS computing device is further configured to:

generate the updated machine pronunciation of the text data according to the pronunciation correction provided by the user.

4. The TTS computing device of claim 1, wherein said TTS computing device is a user computing device in communication with a TTS server.

5. The TTS computing device of claim 4, wherein said TTS computing device is further configured to transmit the pronunciation correction to a TTS crowdsource data source of the TTS server.

6. The TTS computing device of claim 5, wherein the machine pronunciation is derived from the pronunciation correction stored in the TTS crowdsource data source when a number of a plurality of pronunciation corrections exceeds a predetermined threshold.

7. The TTS computing device of claim 6, wherein said TTS computing device is further configured to determine a location of the TTS computing device, wherein the at least one phonetic rule includes determining whether the plurality of pronunciation corrections in the TTS crowdsource data source exceeds a predetermined threshold for a geographic area that includes the location of the TTS computing device.

8. The TTS computing device of claim 1, wherein the machine pronunciation of a text data includes a first machine pronunciation according to at least one first phonetic rule and a second machine pronunciation according to at least one second phonetic rule, said TTS computing device further configured to:

provide both the first and second machine pronunciation to the user interface; and

receive a pronunciation correction from the user, wherein the pronunciation correction is at least one of the first machine pronunciation and the second machine pronunciation provided by the user.

9. A computer-implemented method for correcting pronunciation in a text-to-speech (TTS) system, said method implemented using a TTS computing device in communication with one or more memory devices, said method comprising:

generating a machine pronunciation of a text data according to at least one phonetic rule;

providing the machine pronunciation to a user interface of the TTS computing device such that the machine pronunciation is audibly communicated to a user of the TTS computing device;

receiving a pronunciation correction of the machine pronunciation from the user via the user interface;

determining a first geographic location indicating where the pronunciation correction was provided by the user to the user interface;

storing the pronunciation correction and the first geographic location in a TTS data source;

assigning the pronunciation correction provided by the user to a user profile that corresponds to the text data;

determining a second geographic location indicating where the TTS computing device is currently located;

providing, to the user interface, the machine pronunciation if the second geographic location is outside of a predetermined distance of the first geographic location; and

providing, to the user interface, an updated machine pronunciation based on the pronunciation correction if the second geographic location is within the predetermined distance of the first geographic location.

10. The method of claim 9 further comprising translating the pronunciation correction received from the user from audio data to an updated text data for use in generating the machine pronunciation.

11. The method of claim 10 further comprising:

generating the updated machine pronunciation of the text data according to the pronunciation correction provided by the user.

12. The method of claim 9 wherein the TTS computing device is a user computing device in communication with a TTS server.

13. The method of claim 12 further comprising transmitting the pronunciation correction to a TTS crowdsource data source of the TTS server.

14. The method of claim 13, wherein the machine pronunciation is derived from the pronunciation correction stored in the TTS crowdsource data source when a number of a plurality of pronunciation corrections exceeds a predetermined threshold.

15. The method of claim 14 further comprising determining a location of the TTS computing device, wherein the at least one phonetic rule includes determining whether the plurality of pronunciation corrections for the text data stored in the TTS crowdsource data source exceeds a predetermined threshold for a geographic area that includes the location of the TTS computing device.

16. The method of claim 9, wherein the machine pronunciation of a text data includes a first machine pronunciation according to at least one first phonetic rule and a second machine pronunciation according to at least one second phonetic rule, said method further comprising:

providing both the first and second machine pronunciation to the user interface; and

receiving the pronunciation correction from the user, wherein the pronunciation correction is at least one of the first machine pronunciation and the second machine pronunciation provided by the user.

17. A non-transitory computer readable medium that includes computer executable instructions for correcting pronunciation in a text-to-speech (TTS) system, wherein when executed by a TTS computing device comprising at least one processor in communication with at least one memory device, the computer executable instructions cause the TTS computing device to:

generate a machine pronunciation of a text data according to at least one phonetic rule;

provide the machine pronunciation to a user interface of the TTS computing device such that the machine pronunciation is audibly communicated to a user of the TTS computing device;

receive a pronunciation correction of the machine pronunciation from the user via the user interface;

determine a first geographic location indicating where the pronunciation correction was provided by the user to the user interface;

store the pronunciation correction and the first geographic location in a TTS data source;

assign the pronunciation correction provided by the user to a user profile that corresponds to the text data;

determine a second geographic location indicating where the TTS computing device is currently located;

provide, to the user interface, the machine pronunciation if the second geographic location is outside of a predetermined distance of the first geographic location; and

provide, to the user interface, an updated machine pronunciation based on the pronunciation correction if the second geographic location is within the predetermined distance of the first geographic location.

18. The non-transitory computer readable medium of claim 17, wherein the TTS computing device is a user computing device in communication with a TTS server.