Accent labeling algorithm based on morphological rules and machine learning in English conversion system

The dependency of a speech recognition system on the accent of a user leads to the variation in its performance, as the people from different backgrounds have different accents. Accent labeling and conversion have been reported as a prospective solution for the challenges faced in language learning...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Liu Xiaofeng, Singh Pradeep Kumar, Pavlovich Pljonkin Anton
Formato: article
Lenguaje:EN
Publicado: De Gruyter 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/bf6d7f516c71462e9b3f88b5fadbf7ba
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:bf6d7f516c71462e9b3f88b5fadbf7ba
record_format dspace
spelling oai:doaj.org-article:bf6d7f516c71462e9b3f88b5fadbf7ba2021-12-05T14:10:51ZAccent labeling algorithm based on morphological rules and machine learning in English conversion system2191-026X10.1515/jisys-2020-0144https://doaj.org/article/bf6d7f516c71462e9b3f88b5fadbf7ba2021-07-01T00:00:00Zhttps://doi.org/10.1515/jisys-2020-0144https://doaj.org/toc/2191-026XThe dependency of a speech recognition system on the accent of a user leads to the variation in its performance, as the people from different backgrounds have different accents. Accent labeling and conversion have been reported as a prospective solution for the challenges faced in language learning and various other voice-based advents. In the English TTS system, the accent labeling of unregistered words is another very important link besides the phonetic conversion. Since the importance of the primary stress is much greater than that of the secondary stress, and the primary stress is easier to call than the secondary stress, the labeling of the primary stress is separated from the secondary stress. In this work, the labeling of primary accents uses a labeling algorithm that combines morphological rules and machine learning; the labeling of secondary accents is done entirely through machine learning algorithms. After 10 rounds of cross-validation, the average tagging accuracy rate of primary stress was 94%, the average tagging accuracy rate of secondary stress was 94%, and the total tagging accuracy rate was 83.6%. This perceptual study separates the labeling of primary and secondary accents providing the promising outcomes.Liu XiaofengSingh Pradeep KumarPavlovich Pljonkin AntonDe Gruyterarticletext-to-speech conversionunregistered wordsstress annotationaccent labelingmachine learningScienceQElectronic computers. Computer scienceQA75.5-76.95ENJournal of Intelligent Systems, Vol 30, Iss 1, Pp 881-892 (2021)
institution DOAJ
collection DOAJ
language EN
topic text-to-speech conversion
unregistered words
stress annotation
accent labeling
machine learning
Science
Q
Electronic computers. Computer science
QA75.5-76.95
spellingShingle text-to-speech conversion
unregistered words
stress annotation
accent labeling
machine learning
Science
Q
Electronic computers. Computer science
QA75.5-76.95
Liu Xiaofeng
Singh Pradeep Kumar
Pavlovich Pljonkin Anton
Accent labeling algorithm based on morphological rules and machine learning in English conversion system
description The dependency of a speech recognition system on the accent of a user leads to the variation in its performance, as the people from different backgrounds have different accents. Accent labeling and conversion have been reported as a prospective solution for the challenges faced in language learning and various other voice-based advents. In the English TTS system, the accent labeling of unregistered words is another very important link besides the phonetic conversion. Since the importance of the primary stress is much greater than that of the secondary stress, and the primary stress is easier to call than the secondary stress, the labeling of the primary stress is separated from the secondary stress. In this work, the labeling of primary accents uses a labeling algorithm that combines morphological rules and machine learning; the labeling of secondary accents is done entirely through machine learning algorithms. After 10 rounds of cross-validation, the average tagging accuracy rate of primary stress was 94%, the average tagging accuracy rate of secondary stress was 94%, and the total tagging accuracy rate was 83.6%. This perceptual study separates the labeling of primary and secondary accents providing the promising outcomes.
format article
author Liu Xiaofeng
Singh Pradeep Kumar
Pavlovich Pljonkin Anton
author_facet Liu Xiaofeng
Singh Pradeep Kumar
Pavlovich Pljonkin Anton
author_sort Liu Xiaofeng
title Accent labeling algorithm based on morphological rules and machine learning in English conversion system
title_short Accent labeling algorithm based on morphological rules and machine learning in English conversion system
title_full Accent labeling algorithm based on morphological rules and machine learning in English conversion system
title_fullStr Accent labeling algorithm based on morphological rules and machine learning in English conversion system
title_full_unstemmed Accent labeling algorithm based on morphological rules and machine learning in English conversion system
title_sort accent labeling algorithm based on morphological rules and machine learning in english conversion system
publisher De Gruyter
publishDate 2021
url https://doaj.org/article/bf6d7f516c71462e9b3f88b5fadbf7ba
work_keys_str_mv AT liuxiaofeng accentlabelingalgorithmbasedonmorphologicalrulesandmachinelearninginenglishconversionsystem
AT singhpradeepkumar accentlabelingalgorithmbasedonmorphologicalrulesandmachinelearninginenglishconversionsystem
AT pavlovichpljonkinanton accentlabelingalgorithmbasedonmorphologicalrulesandmachinelearninginenglishconversionsystem
_version_ 1718371687699841024