<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeon-etal-2025-progressive">
    <titleInfo>
        <title>Progressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yejin</namePart>
        <namePart type="family">Jeon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Youngjae</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jihyun</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hyounghun</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gary</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>For individuals who have experienced traumatic events such as strokes, speech may no longer be a viable means of communication. While text-to-speech (TTS) can be used as a communication aid since it generates synthetic speech, it fails to preserve the user’s own voice. As such, face-to-voice (FTV) synthesis, which derives corresponding voices from facial images, provides a promising alternative. However, existing methods rely on pre-trained visual encoders, and finetune them to align with speech embeddings, which strips fine-grained information from facial inputs such as gender or ethnicity, despite their known correlation with vocal traits. Moreover, these pipelines are multi-stage, which requires separate training of multiple components, thus leading to training inefficiency. To address these limitations, we utilize fine-grained facial attribute modeling by decomposing facial images into non-overlapping segments and progressively integrating them into a multi-granular representation. This representation is further refined through multi-task learning of speaker attributes such as gender and ethnicity at both the visual and acoustic domains. Moreover, to improve alignment robustness, we adopt a multi-view training strategy by pairing various visual perspectives of a speaker in terms of different angles and lighting conditions, with identical speech recordings. Extensive subjective and objective evaluations confirm that our approach substantially enhances face-voice congruence and synthesis stability.</abstract>
    <identifier type="citekey">jeon-etal-2025-progressive</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-emnlp.152</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.152/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>2799</start>
            <end>2811</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Progressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesis
%A Jeon, Yejin
%A Kim, Youngjae
%A Lee, Jihyun
%A Kim, Hyounghun
%A Lee, Gary
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F jeon-etal-2025-progressive
%X For individuals who have experienced traumatic events such as strokes, speech may no longer be a viable means of communication. While text-to-speech (TTS) can be used as a communication aid since it generates synthetic speech, it fails to preserve the user’s own voice. As such, face-to-voice (FTV) synthesis, which derives corresponding voices from facial images, provides a promising alternative. However, existing methods rely on pre-trained visual encoders, and finetune them to align with speech embeddings, which strips fine-grained information from facial inputs such as gender or ethnicity, despite their known correlation with vocal traits. Moreover, these pipelines are multi-stage, which requires separate training of multiple components, thus leading to training inefficiency. To address these limitations, we utilize fine-grained facial attribute modeling by decomposing facial images into non-overlapping segments and progressively integrating them into a multi-granular representation. This representation is further refined through multi-task learning of speaker attributes such as gender and ethnicity at both the visual and acoustic domains. Moreover, to improve alignment robustness, we adopt a multi-view training strategy by pairing various visual perspectives of a speaker in terms of different angles and lighting conditions, with identical speech recordings. Extensive subjective and objective evaluations confirm that our approach substantially enhances face-voice congruence and synthesis stability.
%R 10.18653/v1/2025.findings-emnlp.152
%U https://aclanthology.org/2025.findings-emnlp.152/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.152
%P 2799-2811

Markdown (Informal)

[Progressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesis](https://aclanthology.org/2025.findings-emnlp.152/) (Jeon et al., Findings 2025)

• Progressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesis (Jeon et al., Findings 2025)

ACL

• Yejin Jeon, Youngjae Kim, Jihyun Lee, Hyounghun Kim, and Gary Lee. 2025. Progressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesis. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 2799–2811, Suzhou, China. Association for Computational Linguistics.