AUTOMATED TTS SELF CORRECTION SYSTEM

• US 20180197528A1
• Filed: 09/11/2017
• Published: 07/12/2018
• Est. Priority Date: 01/12/2017
• Status: Active Grant

• Current Assignee: Vocollect, Inc. (Honeywell International Inc.)
• Original Assignee: Vocollect, Inc. (Honeywell International Inc.)
• Inventors: Pike, Lori, Hendrickson, James, Volz, Justin
• Granted Patent: US 10,468,015 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• 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 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• 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 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method for text-to-speech (TTS) pronunciation correction includes initiating a correction of a pronunciation error produced by a TTS system; receiving an input from a user for the correction of the pronunciation error; and updating the pronunciation based on the input provided by the user. The user input can include providing one or more voice recording entries, a manual entry from a keyboard, and/or choosing an entry from a predetermined list of phonetic strings. The method can also include pronouncing the corrected pronunciation entry back to the user. The user input can be further used for correction of similar syllables, words, and/or phrases.

Claims

1. A method for text-to-speech (TTS) engine correction, comprising:

identifying, by a TTS engine, an occurrence of an error in a phonetic string pronunciation produced by the TTS engine;

triggering a correction sequence in response to a control signal provided by the user;

prompting the user to enter a correction of the identified error in the phonetic string; and

processing the correction of the phonetic string provided by the user.

2. The method according to claim 1, wherein providing the control signal includes speaking a predetermined control word.

3. The method according to claim 1, wherein providing the control signal includes pressing a predetermined function key.

4. The method according to claim 1, comprising processing the correction provided by the user to correct pronunciation of one or more similar phonetic strings.

5. The method according to claim 1, comprising exchanging the corrected pronunciation of the phonetic string with an external database.

6. The method according to claim 1, wherein the phonetic string includes an abbreviation.

7. A method for text-to-speech (TTS) pronunciation correction, comprising:

initiating, by a user of a TTS system, a correction of a pronunciation error produced by the TTS system;

receiving an input from the user for the correction of the pronunciation error; and

updating the pronunciation based on the input provided by the user.

8. The method according to claim 7, wherein providing the user input comprises providing one or more voice sample recordings.

9. The method according to claim 7, wherein providing the user input comprises selecting a one or more correct phonetics from a predetermined list of pronunciation options.

10. The method according to claim 9, comprising echoing the selected options back to the user.

11. The method according to claim 7, wherein providing the user input comprises entering the correction from a keyboard.

12. The method according to claim 11, comprising echoing the entered correction back to the user.

13. A method for pronunciation improvement, comprising:

receiving a request from an operator of a text-to-speech application to initiate correction of a mispronounced text-to-speech entry;

prompting the operator to enter a corrected pronunciation;

pronouncing the corrected pronunciation entry back to the operator;

prompting the operator to confirm the entry or edit the entry by returning to the entering step; and

replacing the mispronounced entry with the confirmed corrected entry.

14. The method according to claim 13, comprising prompting the operator to select a method of correction from a predetermined list of methods.

15. The method according to claim 14, wherein selecting a method of correction comprises providing one or more voice recording entries, a manual entry from a keyboard, and/or choosing an entry from a predetermined list of phonetic strings.

16. The method according to claim 15, comprising using the operator input to iteratively generate phonetic suggestions for the operator to select.

17. The method according to claim 13, comprising using the confirmed entry to update pronunciation of similar words and/or phrases.

18. The method according to claim 13, wherein receiving a request to initiate correction of a mispronounced entry comprises correction of a misspelled entry.