Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment Article Swipe

PDF

Zhiyu Lin , Jingwen Yang , Jiale Zhao , Meng Liu , Sunzhu Li , Benyou Wang ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2510.20513

Recent speech-to-speech (S2S) models generate intelligible speech but still lack natural expressiveness, largely due to the absence of a reliable evaluation metric. Existing approaches, such as subjective MOS ratings, low-level acoustic features, and emotion recognition are costly, limited, or incomplete. To address this, we present DeEAR (Decoding the Expressive Preference of eAR), a framework that converts human preference for speech expressiveness into an objective score. Grounded in phonetics and psychology, DeEAR evaluates speech across three dimensions: Emotion, Prosody, and Spontaneity, achieving strong alignment with human perception (Spearman's Rank Correlation Coefficient, SRCC = 0.86) using fewer than 500 annotated samples. Beyond reliable scoring, DeEAR enables fair benchmarking and targeted data curation. It not only distinguishes expressiveness gaps across S2S models but also selects 14K expressive utterances to form ExpressiveSpeech, which improves the expressive score (from 2.0 to 23.4 on a 100-point scale) of S2S models. Demos and codes are available at https://github.com/FreedomIntelligence/ExpressiveSpeech

Related Topics

National Institutional Ranking Framework

The Myth Of The Framework

Cynefin Framework

Django (Web Framework)

Iran Nuclear Deal Framework

United Nations Framework Convention On Climate Change

Bootstrap (Front-End Framework)

Electron (Software Framework)

Flask (Web Framework)

Metal–Organic Framework

The Open Group Architecture Framework

Australian Qualifications Framework

Concepts

No concepts available.

Metadata

Type: preprint
Landing Page: http://arxiv.org/abs/2510.20513
PDF: https://arxiv.org/pdf/2510.20513
OA Status: green
OpenAlex ID: https://openalex.org/W4416620132

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416620132

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2510.20513

Digital Object Identifier
Title: Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment

Work title
Type: preprint

OpenAlex work type
Publication year: 2025

Year of publication
Publication date: 2025-10-23

Full publication date if available
Authors: Zhiyu Lin, Jingwen Yang, Jiale Zhao, Meng Liu, Sunzhu Li, Benyou Wang

List of authors in order
Landing page: https://arxiv.org/abs/2510.20513

Publisher landing page
PDF URL: https://arxiv.org/pdf/2510.20513

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/2510.20513

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416620132
doi	https://doi.org/10.48550/arxiv.2510.20513
ids.doi	https://doi.org/10.48550/arxiv.2510.20513
ids.openalex	https://openalex.org/W4416620132
fwci
type	preprint
title	Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language
locations[0].id	pmh:oai:arXiv.org:2510.20513
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/2510.20513
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/2510.20513
locations[1].id	doi:10.48550/arxiv.2510.20513
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
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
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.2510.20513
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5069028297
authorships[0].author.orcid	https://orcid.org/0000-0001-8045-9556
authorships[0].author.display_name	Zhiyu Lin
authorships[0].author_position	first
authorships[0].raw_author_name	Lin, Zhiyu
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5102753054
authorships[1].author.orcid	https://orcid.org/0000-0002-6314-3856
authorships[1].author.display_name	Jingwen Yang
authorships[1].author_position	middle
authorships[1].raw_author_name	Yang, Jingwen
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5049807159
authorships[2].author.orcid	https://orcid.org/0009-0002-7977-3083
authorships[2].author.display_name	Jiale Zhao
authorships[2].author_position	middle
authorships[2].raw_author_name	Zhao, Jiale
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100457527
authorships[3].author.orcid	https://orcid.org/0000-0002-9420-3874
authorships[3].author.display_name	Meng Liu
authorships[3].author_position	middle
authorships[3].raw_author_name	Liu, Meng
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5048281627
authorships[4].author.orcid
authorships[4].author.display_name	Sunzhu Li
authorships[4].author_position	middle
authorships[4].raw_author_name	Li, Sunzhu
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5057282504
authorships[5].author.orcid	https://orcid.org/0000-0002-1501-9914
authorships[5].author.display_name	Benyou Wang
authorships[5].author_position	last
authorships[5].raw_author_name	Wang, Benyou
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/2510.20513
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-25T00:00:00
display_name	Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T18:48:30.529841
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2510.20513
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/2510.20513
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/2510.20513
primary_location.id	pmh:oai:arXiv.org:2510.20513
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/2510.20513
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/2510.20513
publication_date	2025-10-23
publication_year	2025
referenced_works_count	0
abstract_inverted_index.=	91
abstract_inverted_index.a	18, 52, 138
abstract_inverted_index.It	110
abstract_inverted_index.To	40
abstract_inverted_index.an	62
abstract_inverted_index.as	25
abstract_inverted_index.at	149
abstract_inverted_index.in	66
abstract_inverted_index.of	17, 50, 141
abstract_inverted_index.on	137
abstract_inverted_index.or	38
abstract_inverted_index.to	14, 125, 135
abstract_inverted_index.we	43
abstract_inverted_index.14K	122
abstract_inverted_index.2.0	134
abstract_inverted_index.500	96
abstract_inverted_index.MOS	27
abstract_inverted_index.S2S	117, 142
abstract_inverted_index.and	32, 68, 78, 106, 145
abstract_inverted_index.are	35, 147
abstract_inverted_index.but	7, 119
abstract_inverted_index.due	13
abstract_inverted_index.for	58
abstract_inverted_index.not	111
abstract_inverted_index.the	15, 47, 130
abstract_inverted_index.23.4	136
abstract_inverted_index.Rank	87
abstract_inverted_index.SRCC	90
abstract_inverted_index.also	120
abstract_inverted_index.data	108
abstract_inverted_index.fair	104
abstract_inverted_index.form	126
abstract_inverted_index.gaps	115
abstract_inverted_index.into	61
abstract_inverted_index.lack	9
abstract_inverted_index.only	112
abstract_inverted_index.such	24
abstract_inverted_index.than	95
abstract_inverted_index.that	54
abstract_inverted_index.with	83
abstract_inverted_index.(S2S)	2
abstract_inverted_index.(from	133
abstract_inverted_index.0.86)	92
abstract_inverted_index.DeEAR	45, 70, 102
abstract_inverted_index.Demos	144
abstract_inverted_index.codes	146
abstract_inverted_index.eAR),	51
abstract_inverted_index.fewer	94
abstract_inverted_index.human	56, 84
abstract_inverted_index.score	132
abstract_inverted_index.still	8
abstract_inverted_index.this,	42
abstract_inverted_index.three	74
abstract_inverted_index.using	93
abstract_inverted_index.which	128
abstract_inverted_index.Beyond	99
abstract_inverted_index.Recent	0
abstract_inverted_index.across	73, 116
abstract_inverted_index.models	3, 118
abstract_inverted_index.scale)	140
abstract_inverted_index.score.	64
abstract_inverted_index.speech	6, 59, 72
abstract_inverted_index.strong	81
abstract_inverted_index.absence	16
abstract_inverted_index.address	41
abstract_inverted_index.costly,	36
abstract_inverted_index.emotion	33
abstract_inverted_index.enables	103
abstract_inverted_index.largely	12
abstract_inverted_index.metric.	21
abstract_inverted_index.models.	143
abstract_inverted_index.natural	10
abstract_inverted_index.present	44
abstract_inverted_index.selects	121
abstract_inverted_index.Emotion,	76
abstract_inverted_index.Existing	22
abstract_inverted_index.Grounded	65
abstract_inverted_index.Prosody,	77
abstract_inverted_index.acoustic	30
abstract_inverted_index.converts	55
abstract_inverted_index.generate	4
abstract_inverted_index.improves	129
abstract_inverted_index.limited,	37
abstract_inverted_index.ratings,	28
abstract_inverted_index.reliable	19, 100
abstract_inverted_index.samples.	98
abstract_inverted_index.scoring,	101
abstract_inverted_index.targeted	107
abstract_inverted_index.(Decoding	46
abstract_inverted_index.100-point	139
abstract_inverted_index.achieving	80
abstract_inverted_index.alignment	82
abstract_inverted_index.annotated	97
abstract_inverted_index.available	148
abstract_inverted_index.curation.	109
abstract_inverted_index.evaluates	71
abstract_inverted_index.features,	31
abstract_inverted_index.framework	53
abstract_inverted_index.low-level	29
abstract_inverted_index.objective	63
abstract_inverted_index.phonetics	67
abstract_inverted_index.Expressive	48
abstract_inverted_index.Preference	49
abstract_inverted_index.evaluation	20
abstract_inverted_index.expressive	123, 131
abstract_inverted_index.perception	85
abstract_inverted_index.preference	57
abstract_inverted_index.subjective	26
abstract_inverted_index.utterances	124
abstract_inverted_index.(Spearman's	86
abstract_inverted_index.Correlation	88
abstract_inverted_index.approaches,	23
abstract_inverted_index.dimensions:	75
abstract_inverted_index.incomplete.	39
abstract_inverted_index.psychology,	69
abstract_inverted_index.recognition	34
abstract_inverted_index.Coefficient,	89
abstract_inverted_index.Spontaneity,	79
abstract_inverted_index.benchmarking	105
abstract_inverted_index.intelligible	5
abstract_inverted_index.distinguishes	113
abstract_inverted_index.expressiveness	60, 114
abstract_inverted_index.expressiveness,	11
abstract_inverted_index.speech-to-speech	1
abstract_inverted_index.ExpressiveSpeech,	127
abstract_inverted_index.https://github.com/FreedomIntelligence/ExpressiveSpeech	150
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile