@inproceedings{saha-etal-2026-parameter,
title = "Parameter-Efficient Domain Adversarial Training for Lightweight Framewise Phoneme Classification",
author = "Saha, Sohini and
Collins, Leslie M. and
Mainsah, Boyla",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.235/",
pages = "4631--4648",
ISBN = "979-8-89176-444-6",
abstract = "Lightweight neural network models deployed on edge devices are susceptible to performance degradation under unseen acoustic conditions due to domain mismatch between training and deployment environments. This is particularly relevant in causal low latency applications such as cochlear implants (CIs), where limited temporal context and strict computational constraints restrict model robustness. Domain adversarial learning can improve generalization by encouraging representations that are both task-discriminative and domain-invariant; however, jointly learning these representations becomes difficult in limited capacity models. We introduce an adapter-based adversarial learning framework for robust and parameter-efficient domain adaptation. The proposed approach incorporates an adapter module into a pretrained causal backbone. We first establish a robust pretrained baseline network and subsequently perform adversarial adaptation under mismatched acoustic conditions. We evaluate the proposed framework on framewise phonetic group classification to guide phoneme-based time-frequency mask estimation. Empirical results demonstrate consistent improvements in phoneme classification over both standard supervised training and conventional adversarial learning, particularly under low signal-to-noise ratio levels, resulting in statistically significant improvements in objective intelligibility measures of CI vocoded speech."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saha-etal-2026-parameter">
<titleInfo>
<title>Parameter-Efficient Domain Adversarial Training for Lightweight Framewise Phoneme Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sohini</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Collins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boyla</namePart>
<namePart type="family">Mainsah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Lightweight neural network models deployed on edge devices are susceptible to performance degradation under unseen acoustic conditions due to domain mismatch between training and deployment environments. This is particularly relevant in causal low latency applications such as cochlear implants (CIs), where limited temporal context and strict computational constraints restrict model robustness. Domain adversarial learning can improve generalization by encouraging representations that are both task-discriminative and domain-invariant; however, jointly learning these representations becomes difficult in limited capacity models. We introduce an adapter-based adversarial learning framework for robust and parameter-efficient domain adaptation. The proposed approach incorporates an adapter module into a pretrained causal backbone. We first establish a robust pretrained baseline network and subsequently perform adversarial adaptation under mismatched acoustic conditions. We evaluate the proposed framework on framewise phonetic group classification to guide phoneme-based time-frequency mask estimation. Empirical results demonstrate consistent improvements in phoneme classification over both standard supervised training and conventional adversarial learning, particularly under low signal-to-noise ratio levels, resulting in statistically significant improvements in objective intelligibility measures of CI vocoded speech.</abstract>
<identifier type="citekey">saha-etal-2026-parameter</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.235/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>4631</start>
<end>4648</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parameter-Efficient Domain Adversarial Training for Lightweight Framewise Phoneme Classification
%A Saha, Sohini
%A Collins, Leslie M.
%A Mainsah, Boyla
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F saha-etal-2026-parameter
%X Lightweight neural network models deployed on edge devices are susceptible to performance degradation under unseen acoustic conditions due to domain mismatch between training and deployment environments. This is particularly relevant in causal low latency applications such as cochlear implants (CIs), where limited temporal context and strict computational constraints restrict model robustness. Domain adversarial learning can improve generalization by encouraging representations that are both task-discriminative and domain-invariant; however, jointly learning these representations becomes difficult in limited capacity models. We introduce an adapter-based adversarial learning framework for robust and parameter-efficient domain adaptation. The proposed approach incorporates an adapter module into a pretrained causal backbone. We first establish a robust pretrained baseline network and subsequently perform adversarial adaptation under mismatched acoustic conditions. We evaluate the proposed framework on framewise phonetic group classification to guide phoneme-based time-frequency mask estimation. Empirical results demonstrate consistent improvements in phoneme classification over both standard supervised training and conventional adversarial learning, particularly under low signal-to-noise ratio levels, resulting in statistically significant improvements in objective intelligibility measures of CI vocoded speech.
%U https://aclanthology.org/2026.findings-aacl.235/
%P 4631-4648
Markdown (Informal)
[Parameter-Efficient Domain Adversarial Training for Lightweight Framewise Phoneme Classification](https://aclanthology.org/2026.findings-aacl.235/) (Saha et al., Findings 2026)
ACL