Automated TTS self correction system
First Claim
Patent Images
1. A method for text-to-speech (TTS) engine correction, comprising:
- identifying, by a TTS engine, an occurrence of an error in a first 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 first phonetic string;
processing the correction of the first phonetic string provided by the user; and
applying the processed correction to correct pronunciation of at least a second phonetic string by generating an audio signal for playback by the TTS engine, the audio signal comprising the processed correction, wherein the second phonetic string is similar to the first phonetic string.
1 Assignment
0 Petitions
Accused Products
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.
-
Citations
16 Claims
-
1. A method for text-to-speech (TTS) engine correction, comprising:
-
identifying, by a TTS engine, an occurrence of an error in a first 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 first phonetic string; processing the correction of the first phonetic string provided by the user; and applying the processed correction to correct pronunciation of at least a second phonetic string by generating an audio signal for playback by the TTS engine, the audio signal comprising the processed correction, wherein the second phonetic string is similar to the first phonetic string. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A method for text-to-speech (TTS) pronunciation correction, comprising:
-
receiving, based on a control signal from a user, an indication to perform a correction of a pronunciation error produced by a TTS system in a first phonetic string; receiving an input from the user for the correction of the pronunciation error in the first phonetic string; updating the pronunciation of the first phonetic string based on the input provided by the user; applying the correction to correct pronunciation error of at least a second phonetic string, wherein the second phonetic string is similar to the first phonetic string; and generating an audio signal for playback by the TTS system, the audio signal comprising the correction. - View Dependent Claims (7, 8, 9, 10, 11)
-
-
12. A method for pronunciation improvement, comprising:
-
receiving a request from an operator of a text-to-speech application to initiate correction of a first mispronounced text-to-speech entry; prompting the operator to enter a corrected pronunciation for the first mispronounced text-to-speech entry; pronouncing the corrected pronunciation entry back to the operator; prompting the operator to confirm the or edit the by returning to the entering step; replacing the first mispronounced entry with the confirmed corrected entry; updating pronunciation of at least a second word and/or phrase with the confirmed entry, wherein the second word and/or phrase is similar to the first mispronounced entry; and generating an audio signal for playback by a speaker associated with the text-to-speech application, the audio signal comprising the updated pronunciation. - View Dependent Claims (13, 14, 15, 16)
-
Specification