<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2025-seeing">
    <titleInfo>
        <title>Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weiting</namePart>
        <namePart type="family">Tan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiachen</namePart>
        <namePart type="family">Lian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hirofumi</namePart>
        <namePart type="family">Inaguma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paden</namePart>
        <namePart type="family">Tomasello</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Philipp</namePart>
        <namePart type="family">Koehn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xutai</namePart>
        <namePart type="family">Ma</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>We present an Audio-Visual Language Model (AVLM) for expressive speech generation by integrating full-face visual cues into a pre-trained expressive speech model. We explore multiple visual encoders and multimodal fusion strategies during pre-training to identify the most effective integration approach. Subsequent fine-tuning on emotion recognition and expressive dialogue tasks yields substantial gains over speech-only baselines (e.g., +5 F1 in emotion recognition). AVLM highlights the value of expressive visual information in guiding speech generation and offers a foundation for end-to-end multimodal conversational systems.</abstract>
    <identifier type="citekey">tan-etal-2025-seeing</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-emnlp.140</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.140/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>2600</start>
            <end>2617</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation
%A Tan, Weiting
%A Lian, Jiachen
%A Inaguma, Hirofumi
%A Tomasello, Paden
%A Koehn, Philipp
%A Ma, Xutai
%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 tan-etal-2025-seeing
%X We present an Audio-Visual Language Model (AVLM) for expressive speech generation by integrating full-face visual cues into a pre-trained expressive speech model. We explore multiple visual encoders and multimodal fusion strategies during pre-training to identify the most effective integration approach. Subsequent fine-tuning on emotion recognition and expressive dialogue tasks yields substantial gains over speech-only baselines (e.g., +5 F1 in emotion recognition). AVLM highlights the value of expressive visual information in guiding speech generation and offers a foundation for end-to-end multimodal conversational systems.
%R 10.18653/v1/2025.findings-emnlp.140
%U https://aclanthology.org/2025.findings-emnlp.140/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.140
%P 2600-2617

Markdown (Informal)

[Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation](https://aclanthology.org/2025.findings-emnlp.140/) (Tan et al., Findings 2025)

• Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation (Tan et al., Findings 2025)

ACL

• Weiting Tan, Jiachen Lian, Hirofumi Inaguma, Paden Tomasello, Philipp Koehn, and Xutai Ma. 2025. Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 2600–2617, Suzhou, China. Association for Computational Linguistics.