Towards Accurate Phonetic Error Detection Through Phoneme Similarity Modeling

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Xuanru, Lian, Jiachen, Cho, Cheol Jun, Prabhune, Tejas, Li, Shuhe, Li, William, Ortiz, Rodrigo, Ezzes, Zoe, Vonk, Jet, Morin, Brittany, Bogley, Rian, Wauters, Lisa, Miller, Zachary, Gorno-Tempini, Maria, Anumanchipalli, Gopala
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909696232783872
author Zhou, Xuanru
Lian, Jiachen
Cho, Cheol Jun
Prabhune, Tejas
Li, Shuhe
Li, William
Ortiz, Rodrigo
Ezzes, Zoe
Vonk, Jet
Morin, Brittany
Bogley, Rian
Wauters, Lisa
Miller, Zachary
Gorno-Tempini, Maria
Anumanchipalli, Gopala
author_facet Zhou, Xuanru
Lian, Jiachen
Cho, Cheol Jun
Prabhune, Tejas
Li, Shuhe
Li, William
Ortiz, Rodrigo
Ezzes, Zoe
Vonk, Jet
Morin, Brittany
Bogley, Rian
Wauters, Lisa
Miller, Zachary
Gorno-Tempini, Maria
Anumanchipalli, Gopala
contents Phonetic error detection, a core subtask of automatic pronunciation assessment, identifies pronunciation deviations at the phoneme level. Speech variability from accents and dysfluencies challenges accurate phoneme recognition, with current models failing to capture these discrepancies effectively. We propose a verbatim phoneme recognition framework using multi-task training with novel phoneme similarity modeling that transcribes what speakers actually say rather than what they're supposed to say. We develop and open-source \textit{VCTK-accent}, a simulated dataset containing phonetic errors, and propose two novel metrics for assessing pronunciation differences. Our work establishes a new benchmark for phonetic error detection.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14346
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Accurate Phonetic Error Detection Through Phoneme Similarity Modeling
Zhou, Xuanru
Lian, Jiachen
Cho, Cheol Jun
Prabhune, Tejas
Li, Shuhe
Li, William
Ortiz, Rodrigo
Ezzes, Zoe
Vonk, Jet
Morin, Brittany
Bogley, Rian
Wauters, Lisa
Miller, Zachary
Gorno-Tempini, Maria
Anumanchipalli, Gopala
Audio and Speech Processing
Sound
Phonetic error detection, a core subtask of automatic pronunciation assessment, identifies pronunciation deviations at the phoneme level. Speech variability from accents and dysfluencies challenges accurate phoneme recognition, with current models failing to capture these discrepancies effectively. We propose a verbatim phoneme recognition framework using multi-task training with novel phoneme similarity modeling that transcribes what speakers actually say rather than what they're supposed to say. We develop and open-source \textit{VCTK-accent}, a simulated dataset containing phonetic errors, and propose two novel metrics for assessing pronunciation differences. Our work establishes a new benchmark for phonetic error detection.
title Towards Accurate Phonetic Error Detection Through Phoneme Similarity Modeling
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2507.14346