<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="girish-etal-2026-prosody">
    <titleInfo>
        <title>Prosody as Supervision: Bridging the Non-Verbal–Verbal for Multilingual Speech Emotion Recognition</title>
    </titleInfo>
    <name>
        <namePart>Girish</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohd</namePart>
        <namePart type="given">Mujtaba</namePart>
        <namePart type="family">Akhtar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muskaan</namePart>
        <namePart type="family">Singh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>In this work, we introduce a paralinguistic supervision paradigm for low-resource multilingual speech emotion recognition (LRM-SER) that leverages non-verbal vocalizations to exploit prosody-centric emotion cues. Unlike conventional SER systems that rely heavily on labeled verbal speech and suffer from poor cross-lingual transfer, our approach reformulates LRM-SER as non-verbal-to-verbal transfer, where supervision from a labelled non-verbal source domain is adapted to unlabeled verbal speech across multiple target languages. To this end, we propose NOVA-ARC, a geometry-aware framework that models affective structure in the Poincaré ball, discretizes paralinguistic patterns via a hyperbolic vector-quantized prosody codebook, and captures emotion intensity through a hyperbolic emotion lens. For unsupervised adaptation, NOVA-ARC performs optimal-transport-based prototype alignment between source emotion prototypes and target utterances, inducing soft supervision for unlabeled speech while being stabilized through consistency regularization. Experiments show that NOVA-ARC delivers the strongest performance under both non-verbal-to-verbal adaptation and the complementary verbal-to-verbal transfer setting, consistently outperforming Euclidean counter parts and strong SSL baselines. To the best of our knowledge, this work is the first to move beyond verbal-speech–centric supervision by introducing a non-verbal–to–verbal transfer paradigm for SER.</abstract>
    <identifier type="citekey">girish-etal-2026-prosody</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.1940/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>41881</start>
            <end>41893</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prosody as Supervision: Bridging the Non-Verbal–Verbal for Multilingual Speech Emotion Recognition
%A Akhtar, Mohd Mujtaba
%A Singh, Muskaan
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%A Girish
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F girish-etal-2026-prosody
%X In this work, we introduce a paralinguistic supervision paradigm for low-resource multilingual speech emotion recognition (LRM-SER) that leverages non-verbal vocalizations to exploit prosody-centric emotion cues. Unlike conventional SER systems that rely heavily on labeled verbal speech and suffer from poor cross-lingual transfer, our approach reformulates LRM-SER as non-verbal-to-verbal transfer, where supervision from a labelled non-verbal source domain is adapted to unlabeled verbal speech across multiple target languages. To this end, we propose NOVA-ARC, a geometry-aware framework that models affective structure in the Poincaré ball, discretizes paralinguistic patterns via a hyperbolic vector-quantized prosody codebook, and captures emotion intensity through a hyperbolic emotion lens. For unsupervised adaptation, NOVA-ARC performs optimal-transport-based prototype alignment between source emotion prototypes and target utterances, inducing soft supervision for unlabeled speech while being stabilized through consistency regularization. Experiments show that NOVA-ARC delivers the strongest performance under both non-verbal-to-verbal adaptation and the complementary verbal-to-verbal transfer setting, consistently outperforming Euclidean counter parts and strong SSL baselines. To the best of our knowledge, this work is the first to move beyond verbal-speech–centric supervision by introducing a non-verbal–to–verbal transfer paradigm for SER.
%U https://aclanthology.org/2026.acl-long.1940/
%P 41881-41893

Markdown (Informal)

[Prosody as Supervision: Bridging the Non-Verbal–Verbal for Multilingual Speech Emotion Recognition](https://aclanthology.org/2026.acl-long.1940/) (Girish et al., ACL 2026)

• Prosody as Supervision: Bridging the Non-Verbal–Verbal for Multilingual Speech Emotion Recognition (Girish et al., ACL 2026)

ACL

• Girish, Mohd Mujtaba Akhtar, and Muskaan Singh. 2026. Prosody as Supervision: Bridging the Non-Verbal–Verbal for Multilingual Speech Emotion Recognition. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 41881–41893, San Diego, California, United States. Association for Computational Linguistics.