Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data Article Swipe

PDF

Qibing Bai , Sho Inoue , Shuai Wang , Zhongjie Jiang , Yannan Wang , Haizhou Li ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.17735

Accent normalization converts foreign-accented speech into native-like speech while preserving speaker identity. We propose a novel pipeline using self-supervised discrete tokens and non-parallel training data. The system extracts tokens from source speech, converts them through a dedicated model, and synthesizes the output using flow matching. Our method demonstrates superior performance over a frame-to-frame baseline in naturalness, accentedness reduction, and timbre preservation across multiple English accents. Through token-level phonetic analysis, we validate the effectiveness of our token-based approach. We also develop two duration preservation methods, suitable for applications such as dubbing.

Related Topics

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2507.17735
PDF: https://arxiv.org/pdf/2507.17735
OA Status: green
OpenAlex ID: https://openalex.org/W4414886143

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4414886143

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2507.17735

Digital Object Identifier
Title: Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-07-23

Full publication date if available
Authors: Qibing Bai, Sho Inoue, Shuai Wang, Zhongjie Jiang, Yannan Wang, Haizhou Li

List of authors in order
Landing page: https://arxiv.org/abs/2507.17735

Publisher landing page
PDF URL: https://arxiv.org/pdf/2507.17735

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2507.17735

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4414886143
doi	https://doi.org/10.48550/arxiv.2507.17735
ids.doi	https://doi.org/10.48550/arxiv.2507.17735
ids.openalex	https://openalex.org/W4414886143
fwci
type	preprint
title	Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10320
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.5164999961853027
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Neural Networks and Applications
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2507.17735
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2507.17735
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2507.17735
locations[1].id	doi:10.48550/arxiv.2507.17735
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2507.17735
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5065778847
authorships[0].author.orcid
authorships[0].author.display_name	Qibing Bai
authorships[0].author_position	first
authorships[0].raw_author_name	Bai, Qibing
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5108413182
authorships[1].author.orcid
authorships[1].author.display_name	Sho Inoue
authorships[1].author_position	middle
authorships[1].raw_author_name	Inoue, Sho
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100328312
authorships[2].author.orcid	https://orcid.org/0000-0002-7897-2024
authorships[2].author.display_name	Shuai Wang
authorships[2].author_position	middle
authorships[2].raw_author_name	Wang, Shuai
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5101421603
authorships[3].author.orcid	https://orcid.org/0009-0009-7256-6592
authorships[3].author.display_name	Zhongjie Jiang
authorships[3].author_position	middle
authorships[3].raw_author_name	Jiang, Zhongjie
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5084128157
authorships[4].author.orcid	https://orcid.org/0000-0001-7248-4954
authorships[4].author.display_name	Yannan Wang
authorships[4].author_position	middle
authorships[4].raw_author_name	Wang, Yannan
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5032690182
authorships[5].author.orcid	https://orcid.org/0000-0001-9158-9401
authorships[5].author.display_name	Haizhou Li
authorships[5].author_position	last
authorships[5].raw_author_name	Li, Haizhou
authorships[5].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2507.17735
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10320
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.5164999961853027
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Neural Networks and Applications
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2507.17735
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2507.17735
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2507.17735
primary_location.id	pmh:oai:arXiv.org:2507.17735
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2507.17735
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2507.17735
publication_date	2025-07-23
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	14, 35, 51
abstract_inverted_index.We	12, 77
abstract_inverted_index.as	88
abstract_inverted_index.in	54
abstract_inverted_index.of	73
abstract_inverted_index.we	69
abstract_inverted_index.Our	45
abstract_inverted_index.The	25
abstract_inverted_index.and	21, 38, 58
abstract_inverted_index.for	85
abstract_inverted_index.our	74
abstract_inverted_index.the	40, 71
abstract_inverted_index.two	80
abstract_inverted_index.also	78
abstract_inverted_index.flow	43
abstract_inverted_index.from	29
abstract_inverted_index.into	5
abstract_inverted_index.over	50
abstract_inverted_index.such	87
abstract_inverted_index.them	33
abstract_inverted_index.data.	24
abstract_inverted_index.novel	15
abstract_inverted_index.using	17, 42
abstract_inverted_index.while	8
abstract_inverted_index.Accent	0
abstract_inverted_index.across	61
abstract_inverted_index.method	46
abstract_inverted_index.model,	37
abstract_inverted_index.output	41
abstract_inverted_index.source	30
abstract_inverted_index.speech	4, 7
abstract_inverted_index.system	26
abstract_inverted_index.timbre	59
abstract_inverted_index.tokens	20, 28
abstract_inverted_index.English	63
abstract_inverted_index.Through	65
abstract_inverted_index.develop	79
abstract_inverted_index.propose	13
abstract_inverted_index.speaker	10
abstract_inverted_index.speech,	31
abstract_inverted_index.through	34
abstract_inverted_index.accents.	64
abstract_inverted_index.baseline	53
abstract_inverted_index.converts	2, 32
abstract_inverted_index.discrete	19
abstract_inverted_index.dubbing.	89
abstract_inverted_index.duration	81
abstract_inverted_index.extracts	27
abstract_inverted_index.methods,	83
abstract_inverted_index.multiple	62
abstract_inverted_index.phonetic	67
abstract_inverted_index.pipeline	16
abstract_inverted_index.suitable	84
abstract_inverted_index.superior	48
abstract_inverted_index.training	23
abstract_inverted_index.validate	70
abstract_inverted_index.analysis,	68
abstract_inverted_index.approach.	76
abstract_inverted_index.dedicated	36
abstract_inverted_index.identity.	11
abstract_inverted_index.matching.	44
abstract_inverted_index.preserving	9
abstract_inverted_index.reduction,	57
abstract_inverted_index.native-like	6
abstract_inverted_index.performance	49
abstract_inverted_index.synthesizes	39
abstract_inverted_index.token-based	75
abstract_inverted_index.token-level	66
abstract_inverted_index.accentedness	56
abstract_inverted_index.applications	86
abstract_inverted_index.demonstrates	47
abstract_inverted_index.naturalness,	55
abstract_inverted_index.non-parallel	22
abstract_inverted_index.preservation	60, 82
abstract_inverted_index.effectiveness	72
abstract_inverted_index.normalization	1
abstract_inverted_index.frame-to-frame	52
abstract_inverted_index.self-supervised	18
abstract_inverted_index.foreign-accented	3
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile