@inproceedings{samin-etal-2025-investigating,
title = "Investigating Adapters for Parameter-efficient Low-resource Automatic Speech Recognition",
author = "Samin, Ahnaf Mozib and
Nayak, Shekhar and
De Marco, Andrea and
Borg, Claudia",
editor = "Adlakha, Vaibhav and
Chronopoulou, Alexandra and
Li, Xiang Lorraine and
Majumder, Bodhisattwa Prasad and
Shi, Freda and
Vernikos, Giorgos",
booktitle = "Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025)",
month = may,
year = "2025",
address = "Albuquerque, NM",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.repl4nlp-1.8/",
doi = "10.18653/v1/2025.repl4nlp-1.8",
pages = "100--107",
ISBN = "979-8-89176-245-9",
abstract = "Recent years have witnessed the adoption of parameter-efficient adapters in pre-trained language models for natural language processing. Yet, their application in speech processing remains less studied. In this work, we explore the adapters for low-resource speech recognition, introducing a novel technique - ConvAdapt into pre-trained speech models. We investigate various aspects such as data requirements, transfer learning within adapters, and scaling of feed-forward layers in adapters. Our findings reveal that bottleneck adapters offer competitiveness with full fine-tuning with at least 10 hours of data, but they are not as effective in few-shot learning scenarios. Notably, ConvAdapt demonstrates improved performance in such cases. In addition, transfer learning in adapters shows promise, necessitating research in related languages. Furthermore, employing larger speech models for adapter-tuning surpasses fine-tuning with ample data, potentially due to reduced overfitting than fine-tuning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="samin-etal-2025-investigating">
<titleInfo>
<title>Investigating Adapters for Parameter-efficient Low-resource Automatic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahnaf</namePart>
<namePart type="given">Mozib</namePart>
<namePart type="family">Samin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shekhar</namePart>
<namePart type="family">Nayak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">De Marco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Borg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vaibhav</namePart>
<namePart type="family">Adlakha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Chronopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="given">Lorraine</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bodhisattwa</namePart>
<namePart type="given">Prasad</namePart>
<namePart type="family">Majumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Freda</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giorgos</namePart>
<namePart type="family">Vernikos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, NM</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-245-9</identifier>
</relatedItem>
<abstract>Recent years have witnessed the adoption of parameter-efficient adapters in pre-trained language models for natural language processing. Yet, their application in speech processing remains less studied. In this work, we explore the adapters for low-resource speech recognition, introducing a novel technique - ConvAdapt into pre-trained speech models. We investigate various aspects such as data requirements, transfer learning within adapters, and scaling of feed-forward layers in adapters. Our findings reveal that bottleneck adapters offer competitiveness with full fine-tuning with at least 10 hours of data, but they are not as effective in few-shot learning scenarios. Notably, ConvAdapt demonstrates improved performance in such cases. In addition, transfer learning in adapters shows promise, necessitating research in related languages. Furthermore, employing larger speech models for adapter-tuning surpasses fine-tuning with ample data, potentially due to reduced overfitting than fine-tuning.</abstract>
<identifier type="citekey">samin-etal-2025-investigating</identifier>
<identifier type="doi">10.18653/v1/2025.repl4nlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2025.repl4nlp-1.8/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>100</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Adapters for Parameter-efficient Low-resource Automatic Speech Recognition
%A Samin, Ahnaf Mozib
%A Nayak, Shekhar
%A De Marco, Andrea
%A Borg, Claudia
%Y Adlakha, Vaibhav
%Y Chronopoulou, Alexandra
%Y Li, Xiang Lorraine
%Y Majumder, Bodhisattwa Prasad
%Y Shi, Freda
%Y Vernikos, Giorgos
%S Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, NM
%@ 979-8-89176-245-9
%F samin-etal-2025-investigating
%X Recent years have witnessed the adoption of parameter-efficient adapters in pre-trained language models for natural language processing. Yet, their application in speech processing remains less studied. In this work, we explore the adapters for low-resource speech recognition, introducing a novel technique - ConvAdapt into pre-trained speech models. We investigate various aspects such as data requirements, transfer learning within adapters, and scaling of feed-forward layers in adapters. Our findings reveal that bottleneck adapters offer competitiveness with full fine-tuning with at least 10 hours of data, but they are not as effective in few-shot learning scenarios. Notably, ConvAdapt demonstrates improved performance in such cases. In addition, transfer learning in adapters shows promise, necessitating research in related languages. Furthermore, employing larger speech models for adapter-tuning surpasses fine-tuning with ample data, potentially due to reduced overfitting than fine-tuning.
%R 10.18653/v1/2025.repl4nlp-1.8
%U https://aclanthology.org/2025.repl4nlp-1.8/
%U https://doi.org/10.18653/v1/2025.repl4nlp-1.8
%P 100-107
Markdown (Informal)
[Investigating Adapters for Parameter-efficient Low-resource Automatic Speech Recognition](https://aclanthology.org/2025.repl4nlp-1.8/) (Samin et al., RepL4NLP 2025)
ACL