Conversion of text-to-speech pronunciation outputs to hyperarticulated vowels
In non-limiting examples of the present disclosure, systems, methods and devices for mapping hyperarticulated sounds to text units are presented. A plurality of textual units may be received. The plurality of textual units may be processed with a natural language processing engine. A sentence structure for the plurality of textual units may be identified, wherein the sentence structure comprises a plurality of words. The plurality of words may be processed with a text-to-speech engine. A text-to-speech output comprising a plurality of pronunciations may be identified, wherein each of the plurality of pronunciations corresponds to a syllabic unit of one of the plurality of words. A hyperarticulated vowel sound may be mapped to each syllabic unit from the text-to-speech output. A pronunciation instruction corresponding to each hyperarticulated vowel sound may be caused to be surfaced.
1. A method for mapping hyperarticulated sounds to text units, the method comprising:
receiving a plurality of textual units;
processing the plurality of textual units with a natural language processing engine;
identifying, based on the processing with the natural language processing engine, a sentence structure for the plurality of textual units, wherein the sentence structure comprises a plurality of words;
processing the plurality of words with a text-to-speech engine;
identifying, based on the processing with the text-to-speech engine, a text-to-speech output comprising a plurality of pronunciations, wherein each of plurality of pronunciations corresponds to a syllabic unit of one of the plurality of words;
identifying, utilizing a syllabification engine, a syllabification engine output comprising at least one syllable for each of the plurality of words;
aligning, for each of the plurality of words, the syllabification engine output and the text-to-speech output to identify a consensus set of syllables;
mapping a hyperarticulated vowel sound to each of the consensus set of syllables; and
displaying, in the plurality of textual units, a display element corresponding to each mapped hyperarticulated vowel sound in association with its corresponding syllable of the consensus set of syllables.
2. The method of claim 1 , further comprising:
processing the plurality of words with a language detection engine; and
identifying, based on the processing with the language detection engine, a language associated with the plurality of words.
3. The method of claim 1 , wherein aligning the syllabification engine output and the text-to-speech output to identify a consensus set of syllables comprises:
determining, for each of the plurality of words, that there is a syllabic unit from the text-to-speech output that has a corresponding syllable from the syllabification engine.
4. The method of claim 3 , further comprising:
determining that the syllabification engine output and the text-to-speech output cannot be aligned for at least one of the plurality of words; and
identifying correct syllabification for the at least one word from a manually curated syllabification table.
5. The method of claim 1 , wherein each display element displayed in the plurality of textual units comprises an image of an object with a name having a vowel sound in it corresponding to an associated hyperarticulated vowel sound.
6. The method of claim 5 , wherein each name for each object is a monosyllabic name.
7. The method of claim 1 , wherein the syllabification engine utilizes a lexicon and artificial intelligence to identify the syllabification engine output.
8. A system for mapping hyperarticulated sounds to text units, comprising:
a memory for storing executable program code; and
one or more processors, functionally coupled to the memory, the one or more processors being responsive to computer-executable instructions contained in the program code and operative to:
receive a plurality of textual units;
process the plurality of textual units with a natural language processing engine;
identify, based on the processing with the natural language processing engine, a sentence structure for the plurality of textual units, wherein the sentence structure comprises a plurality of words;
process the plurality of words with a text-to-speech engine;
identify, based on the processing with the text-to-speech engine, a text-to-speech output comprising a plurality of pronunciations, wherein each of the plurality of pronunciations corresponds to a syllabic unit of one of the plurality of words;
identify, utilizing a syllabification engine, a syllabification engine output comprising at least one syllable for each of the plurality of words;
align, for each of the plurality of words, the syllabification engine output and the text-to-speech output to identify a consensus set of syllables;
map a hyperarticulated vowel sound to each of the consensus set of syllables; and
display, in the plurality of textual units, a display element corresponding to each mapped hyperarticulated vowel sound in association with its corresponding syllable of the consensus set of syllables.
9. The system of claim 8 , wherein in aligning the syllabification engine output and the text-to-speech output to identify a consensus set of syllables, the one or more processors are further responsive to the computer-executable instructions contained in the program code and operative to:
determine, for each of the plurality of words, that there is a syllabic unit from the text-to-speech output that has a corresponding syllable from the syllabification engine.
10. The system of claim 9 , wherein the one or more processors are further responsive to the computer-executable instructions contained in the program code and operative to:
determine that the syllabification engine output and the text-to-speech output cannot be aligned for at least one of the plurality of words; and
identify correct syllabification for the at least one word from a manually curated syllabification table.
11. The system of claim 8 , wherein each display element displayed in the plurality of textual units comprises an image of an object with a monosyllabic name having a vowel sound in it corresponding to a hyperarticulated vowel sound for a syllable in a word that the display element is displayed in association with.
12. The system of claim 8 , wherein the syllabification engine utilizes a lexicon and artificial intelligence to identify the syllabification engine output.
13. A computer-readable storage device comprising executable instructions that, when executed by one or more processors, assists with mapping hyperarticulated sounds to text units, the computer-readable storage device including instructions executable by the one or more processors for:
receiving a plurality of textual units;
processing the plurality of textual units with a natural language processing engine;
identifying, based on the processing with the natural language processing engine, a sentence structure for the plurality of textual units, wherein the sentence structure comprises a plurality of words;
processing the plurality of words with a text-to-speech engine;
identifying, based on the processing with the text-to-speech engine, a text-to-speech output comprising a plurality of pronunciations, wherein each of plurality of pronunciations corresponds to a syllabic unit of one of the plurality of words;
identifying, utilizing a syllabification engine, a syllabification engine output comprising at least one syllable for each of the plurality of words;
aligning, for each of the plurality of words, the syllabification engine output and the text-to-speech output to identify a consensus set of syllables;
mapping a hyperarticulated vowel sound to each of the consensus set of syllables; and
displaying, in the plurality of textual units, a display element corresponding to each mapped hyperarticulated vowel sound in association with its corresponding syllable of the consensus set of syllables.
14. The computer-readable storage device of claim 13 , wherein in aligning the syllabification engine output and the text-to-speech output to identify a consensus set of syllables, the instructions are further executable by the one or more processors for:
determining, for each of the plurality of words, that there is a syllabic unit from the text-to-speech output that has a corresponding syllable from the syllabification engine.
15. The computer-readable storage device of claim 14 , wherein the instructions are further executable by the one or more processors for:
determining that the syllabification engine output and the text-to-speech output cannot be aligned for at least one of the plurality of words; and
identifying correct syllabification for the at least one word from a manually curated syllabification table.
16. The computer-readable storage device of claim 13 , wherein the syllabification engine utilizes a lexicon and artificial intelligence to identify the syllabification engine output.
17. The computer-readable storage device of claim 13 , wherein each display element displayed in the plurality of textual units comprises an image of an object with a name having a vowel sound in it corresponding to an associated hyperarticulated vowel sound.
18. The computer-readable storage device of claim 13 , wherein each name for each object is a monosyllabic name.