Hierarchical Control of Emotion Rendering in Speech Synthesis Article Swipe

PDF

Sho Inoue , Kun Zhou , Shuai Wang , Haizhou Li ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2412.12498

Emotional text-to-speech synthesis (TTS) aims to generate realistic emotional speech from input text. However, quantitatively controlling multi-level emotion rendering remains challenging. In this paper, we propose a flow-matching based emotional TTS framework with a novel approach for emotion intensity modeling to facilitate fine-grained control over emotion rendering at the phoneme, word, and utterance levels. We introduce a hierarchical emotion distribution (ED) extractor that captures a quantifiable ED embedding across different speech segment levels. Additionally, we explore various acoustic features and assess their impact on emotion intensity modeling. During TTS training, the hierarchical ED embedding effectively captures the variance in emotion intensity from the reference audio and correlates it with linguistic and speaker information. The TTS model not only generates emotional speech during inference, but also quantitatively controls the emotion rendering over the speech constituents. Both objective and subjective evaluations demonstrate the effectiveness of our framework in terms of speech quality, emotional expressiveness, and hierarchical emotion control.

Related Topics

Rendering (Computer Graphics)

Computer Science

Artificial Intelligence

Concepts

Rendering (computer graphics) Computer science Control (management) Speech recognition Speech synthesis Psychology Artificial intelligence

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2412.12498
PDF: https://arxiv.org/pdf/2412.12498
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4405562097

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4405562097

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2412.12498

Digital Object Identifier
Title: Hierarchical Control of Emotion Rendering in Speech Synthesis

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-12-17

Full publication date if available
Authors: Sho Inoue, Kun Zhou, Shuai Wang, Haizhou Li

List of authors in order
Landing page: https://arxiv.org/abs/2412.12498

Publisher landing page
PDF URL: https://arxiv.org/pdf/2412.12498

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/2412.12498

Direct OA link when available
Concepts: Rendering (computer graphics), Computer science, Control (management), Speech recognition, Speech synthesis, Psychology, Artificial intelligence

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4405562097
doi	https://doi.org/10.48550/arxiv.2412.12498
ids.doi	https://doi.org/10.48550/arxiv.2412.12498
ids.openalex	https://openalex.org/W4405562097
fwci
type	preprint
title	Hierarchical Control of Emotion Rendering in Speech Synthesis
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11448
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.7978000044822693
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Face recognition and analysis
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C205711294
concepts[0].level	2
concepts[0].score	0.8002371788024902
concepts[0].wikidata	https://www.wikidata.org/wiki/Q176953
concepts[0].display_name	Rendering (computer graphics)
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.5059546828269958
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C2775924081
concepts[2].level	2
concepts[2].score	0.41879093647003174
concepts[2].wikidata	https://www.wikidata.org/wiki/Q55608371
concepts[2].display_name	Control (management)
concepts[3].id	https://openalex.org/C28490314
concepts[3].level	1
concepts[3].score	0.4170069098472595
concepts[3].wikidata	https://www.wikidata.org/wiki/Q189436
concepts[3].display_name	Speech recognition
concepts[4].id	https://openalex.org/C14999030
concepts[4].level	2
concepts[4].score	0.4136335253715515
concepts[4].wikidata	https://www.wikidata.org/wiki/Q16346
concepts[4].display_name	Speech synthesis
concepts[5].id	https://openalex.org/C15744967
concepts[5].level	0
concepts[5].score	0.34474629163742065
concepts[5].wikidata	https://www.wikidata.org/wiki/Q9418
concepts[5].display_name	Psychology
concepts[6].id	https://openalex.org/C154945302
concepts[6].level	1
concepts[6].score	0.23402506113052368
concepts[6].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[6].display_name	Artificial intelligence
keywords[0].id	https://openalex.org/keywords/rendering
keywords[0].score	0.8002371788024902
keywords[0].display_name	Rendering (computer graphics)
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.5059546828269958
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/control
keywords[2].score	0.41879093647003174
keywords[2].display_name	Control (management)
keywords[3].id	https://openalex.org/keywords/speech-recognition
keywords[3].score	0.4170069098472595
keywords[3].display_name	Speech recognition
keywords[4].id	https://openalex.org/keywords/speech-synthesis
keywords[4].score	0.4136335253715515
keywords[4].display_name	Speech synthesis
keywords[5].id	https://openalex.org/keywords/psychology
keywords[5].score	0.34474629163742065
keywords[5].display_name	Psychology
keywords[6].id	https://openalex.org/keywords/artificial-intelligence
keywords[6].score	0.23402506113052368
keywords[6].display_name	Artificial intelligence
language	en
locations[0].id	pmh:oai:arXiv.org:2412.12498
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/2412.12498
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/2412.12498
locations[1].id	doi:10.48550/arxiv.2412.12498
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.2412.12498
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5108413182
authorships[0].author.orcid
authorships[0].author.display_name	Sho Inoue
authorships[0].author_position	first
authorships[0].raw_author_name	Inoue, Sho
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5101654458
authorships[1].author.orcid	https://orcid.org/0000-0002-7869-4474
authorships[1].author.display_name	Kun Zhou
authorships[1].author_position	middle
authorships[1].raw_author_name	Zhou, Kun
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/A5032690182
authorships[3].author.orcid	https://orcid.org/0000-0001-9158-9401
authorships[3].author.display_name	Haizhou Li
authorships[3].author_position	last
authorships[3].raw_author_name	Li, Haizhou
authorships[3].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/2412.12498
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Hierarchical Control of Emotion Rendering in Speech Synthesis
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11448
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.7978000044822693
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Face recognition and analysis
related_works	https://openalex.org/W4391375266, https://openalex.org/W2748952813, https://openalex.org/W2931662336, https://openalex.org/W2077865380, https://openalex.org/W3006817050, https://openalex.org/W4401768695, https://openalex.org/W2765597752, https://openalex.org/W2134894512, https://openalex.org/W2083375246, https://openalex.org/W2067108088
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2412.12498
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/2412.12498
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/2412.12498
primary_location.id	pmh:oai:arXiv.org:2412.12498
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/2412.12498
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/2412.12498
publication_date	2024-12-17
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	26, 33, 56, 64
abstract_inverted_index.ED	66, 92
abstract_inverted_index.In	21
abstract_inverted_index.We	54
abstract_inverted_index.at	47
abstract_inverted_index.in	98, 145
abstract_inverted_index.it	107
abstract_inverted_index.of	142, 147
abstract_inverted_index.on	83
abstract_inverted_index.to	5, 40
abstract_inverted_index.we	24, 74
abstract_inverted_index.TTS	30, 88, 114
abstract_inverted_index.The	113
abstract_inverted_index.and	51, 79, 105, 110, 136, 152
abstract_inverted_index.but	123
abstract_inverted_index.for	36
abstract_inverted_index.not	116
abstract_inverted_index.our	143
abstract_inverted_index.the	48, 90, 96, 102, 127, 131, 140
abstract_inverted_index.(ED)	60
abstract_inverted_index.Both	134
abstract_inverted_index.aims	4
abstract_inverted_index.also	124
abstract_inverted_index.from	10, 101
abstract_inverted_index.only	117
abstract_inverted_index.over	44, 130
abstract_inverted_index.that	62
abstract_inverted_index.this	22
abstract_inverted_index.with	32, 108
abstract_inverted_index.(TTS)	3
abstract_inverted_index.audio	104
abstract_inverted_index.based	28
abstract_inverted_index.input	11
abstract_inverted_index.model	115
abstract_inverted_index.novel	34
abstract_inverted_index.terms	146
abstract_inverted_index.text.	12
abstract_inverted_index.their	81
abstract_inverted_index.word,	50
abstract_inverted_index.During	87
abstract_inverted_index.across	68
abstract_inverted_index.assess	80
abstract_inverted_index.during	121
abstract_inverted_index.impact	82
abstract_inverted_index.paper,	23
abstract_inverted_index.speech	9, 70, 120, 132, 148
abstract_inverted_index.control	43
abstract_inverted_index.emotion	17, 37, 45, 58, 84, 99, 128, 154
abstract_inverted_index.explore	75
abstract_inverted_index.levels.	53, 72
abstract_inverted_index.propose	25
abstract_inverted_index.remains	19
abstract_inverted_index.segment	71
abstract_inverted_index.speaker	111
abstract_inverted_index.various	76
abstract_inverted_index.However,	13
abstract_inverted_index.acoustic	77
abstract_inverted_index.approach	35
abstract_inverted_index.captures	63, 95
abstract_inverted_index.control.	155
abstract_inverted_index.controls	126
abstract_inverted_index.features	78
abstract_inverted_index.generate	6
abstract_inverted_index.modeling	39
abstract_inverted_index.phoneme,	49
abstract_inverted_index.quality,	149
abstract_inverted_index.variance	97
abstract_inverted_index.Emotional	0
abstract_inverted_index.different	69
abstract_inverted_index.embedding	67, 93
abstract_inverted_index.emotional	8, 29, 119, 150
abstract_inverted_index.extractor	61
abstract_inverted_index.framework	31, 144
abstract_inverted_index.generates	118
abstract_inverted_index.intensity	38, 85, 100
abstract_inverted_index.introduce	55
abstract_inverted_index.modeling.	86
abstract_inverted_index.objective	135
abstract_inverted_index.realistic	7
abstract_inverted_index.reference	103
abstract_inverted_index.rendering	18, 46, 129
abstract_inverted_index.synthesis	2
abstract_inverted_index.training,	89
abstract_inverted_index.utterance	52
abstract_inverted_index.correlates	106
abstract_inverted_index.facilitate	41
abstract_inverted_index.inference,	122
abstract_inverted_index.linguistic	109
abstract_inverted_index.subjective	137
abstract_inverted_index.controlling	15
abstract_inverted_index.demonstrate	139
abstract_inverted_index.effectively	94
abstract_inverted_index.evaluations	138
abstract_inverted_index.multi-level	16
abstract_inverted_index.challenging.	20
abstract_inverted_index.distribution	59
abstract_inverted_index.fine-grained	42
abstract_inverted_index.hierarchical	57, 91, 153
abstract_inverted_index.information.	112
abstract_inverted_index.quantifiable	65
abstract_inverted_index.Additionally,	73
abstract_inverted_index.constituents.	133
abstract_inverted_index.effectiveness	141
abstract_inverted_index.flow-matching	27
abstract_inverted_index.quantitatively	14, 125
abstract_inverted_index.text-to-speech	1
abstract_inverted_index.expressiveness,	151
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile