@inproceedings{balakrishnan-thayasivam-2026-quality,
title = "Quality-Aware Adversarial Ensemble for Singer Identification in 1960s {T}amil Film Music",
author = "Balakrishnan, Sathiyakugan and
Thayasivam, Uthayasanker",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.10/",
pages = "150--159",
ISBN = "979-8-89176-383-8",
abstract = "1960s Tamil cinema{'}s musical heritage lacks adequate metadata identifying playback singers in archival recordings. We present a quality-aware adversarial ensemble approach addressing two critical challenges: (1) variable audio degradation requiring adaptive model selection, and (2) instrumentation leakage confounding singer-specific features. We curate 348 annotated clips (12 hours) spanning 48 singers from 179 films. Our methodology introduces: a reliability estimation network dynamically gating five complementary pre-trained speaker models (Wav2Vec2, ECAPA-TDNN, WeSpeaker, CAM++, ERes2NetV2) based on degradation characteristics; adversarial training disentangling singer identity from accompaniment style; and uncertainty-calibrated predictions for human-in-the-loop workflows. On a held-out test set of 52 clips, we achieve 96.2{\%} accuracy (95{\%} CI: [87.5{\%}, 99.2{\%}]) and 2.0{\%} EER (95{\%} CI: [1.2{\%}, 3.1{\%}]), representing 7.7{\%} absolute improvement over the best single model and 2.0{\%} over static ensemble fusion. Ablations show quality-aware gating contributes 2.0{\%} and adversarial disentanglement 2.0{\%} beyond standard ensembles. We publicly release the dataset and code with fixed splits."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balakrishnan-thayasivam-2026-quality">
<titleInfo>
<title>Quality-Aware Adversarial Ensemble for Singer Identification in 1960s Tamil Film Music</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sathiyakugan</namePart>
<namePart type="family">Balakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uthayasanker</namePart>
<namePart type="family">Thayasivam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>1960s Tamil cinema’s musical heritage lacks adequate metadata identifying playback singers in archival recordings. We present a quality-aware adversarial ensemble approach addressing two critical challenges: (1) variable audio degradation requiring adaptive model selection, and (2) instrumentation leakage confounding singer-specific features. We curate 348 annotated clips (12 hours) spanning 48 singers from 179 films. Our methodology introduces: a reliability estimation network dynamically gating five complementary pre-trained speaker models (Wav2Vec2, ECAPA-TDNN, WeSpeaker, CAM++, ERes2NetV2) based on degradation characteristics; adversarial training disentangling singer identity from accompaniment style; and uncertainty-calibrated predictions for human-in-the-loop workflows. On a held-out test set of 52 clips, we achieve 96.2% accuracy (95% CI: [87.5%, 99.2%]) and 2.0% EER (95% CI: [1.2%, 3.1%]), representing 7.7% absolute improvement over the best single model and 2.0% over static ensemble fusion. Ablations show quality-aware gating contributes 2.0% and adversarial disentanglement 2.0% beyond standard ensembles. We publicly release the dataset and code with fixed splits.</abstract>
<identifier type="citekey">balakrishnan-thayasivam-2026-quality</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.10/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>150</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quality-Aware Adversarial Ensemble for Singer Identification in 1960s Tamil Film Music
%A Balakrishnan, Sathiyakugan
%A Thayasivam, Uthayasanker
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F balakrishnan-thayasivam-2026-quality
%X 1960s Tamil cinema’s musical heritage lacks adequate metadata identifying playback singers in archival recordings. We present a quality-aware adversarial ensemble approach addressing two critical challenges: (1) variable audio degradation requiring adaptive model selection, and (2) instrumentation leakage confounding singer-specific features. We curate 348 annotated clips (12 hours) spanning 48 singers from 179 films. Our methodology introduces: a reliability estimation network dynamically gating five complementary pre-trained speaker models (Wav2Vec2, ECAPA-TDNN, WeSpeaker, CAM++, ERes2NetV2) based on degradation characteristics; adversarial training disentangling singer identity from accompaniment style; and uncertainty-calibrated predictions for human-in-the-loop workflows. On a held-out test set of 52 clips, we achieve 96.2% accuracy (95% CI: [87.5%, 99.2%]) and 2.0% EER (95% CI: [1.2%, 3.1%]), representing 7.7% absolute improvement over the best single model and 2.0% over static ensemble fusion. Ablations show quality-aware gating contributes 2.0% and adversarial disentanglement 2.0% beyond standard ensembles. We publicly release the dataset and code with fixed splits.
%U https://aclanthology.org/2026.eacl-srw.10/
%P 150-159
Markdown (Informal)
[Quality-Aware Adversarial Ensemble for Singer Identification in 1960s Tamil Film Music](https://aclanthology.org/2026.eacl-srw.10/) (Balakrishnan & Thayasivam, EACL 2026)
ACL