@inproceedings{chen-etal-2024-meta,
title = "Meta-Adapter for Self-Supervised Speech Models: A Solution to Low-Resource Speech Recognition Challenges",
author = "Chen, Yaqi and
Zhang, Hao and
Yang, Xukui and
Zhang, Wenlin and
Qu, Dan",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.979",
pages = "11215--11221",
abstract = "Self-supervised models have demonstrated remarkable performance in speech processing by learning latent representations from large amounts of unlabeled data. Although these models yield promising results on low-resource languages, the computational expense of fine-tuning all model parameters is prohibitively high. Adapters offer a solution by incorporating lightweight bottleneck structures into pre-trained models, enabling efficient parameter adaptation for downstream tasks. However, randomly initialized adapters often underperform in low-resource scenarios, limiting their applicability in low-resource languages. To address this issue, we develop the Meta-Adapter for self-supervised models to obtain meta-initialized parameters that facilitate quick adaptation to low-resource languages. Extensive experiments on the Common Voice and FLEURS datasets demonstrate the superior performance of Meta-Adapters on 12 low-resource languages spanning four different language families. Moreover, Meta-adapters show better generalization and extensibility than traditional pretraining methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-meta">
<titleInfo>
<title>Meta-Adapter for Self-Supervised Speech Models: A Solution to Low-Resource Speech Recognition Challenges</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xukui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenlin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Self-supervised models have demonstrated remarkable performance in speech processing by learning latent representations from large amounts of unlabeled data. Although these models yield promising results on low-resource languages, the computational expense of fine-tuning all model parameters is prohibitively high. Adapters offer a solution by incorporating lightweight bottleneck structures into pre-trained models, enabling efficient parameter adaptation for downstream tasks. However, randomly initialized adapters often underperform in low-resource scenarios, limiting their applicability in low-resource languages. To address this issue, we develop the Meta-Adapter for self-supervised models to obtain meta-initialized parameters that facilitate quick adaptation to low-resource languages. Extensive experiments on the Common Voice and FLEURS datasets demonstrate the superior performance of Meta-Adapters on 12 low-resource languages spanning four different language families. Moreover, Meta-adapters show better generalization and extensibility than traditional pretraining methods.</abstract>
<identifier type="citekey">chen-etal-2024-meta</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.979</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11215</start>
<end>11221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Meta-Adapter for Self-Supervised Speech Models: A Solution to Low-Resource Speech Recognition Challenges
%A Chen, Yaqi
%A Zhang, Hao
%A Yang, Xukui
%A Zhang, Wenlin
%A Qu, Dan
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F chen-etal-2024-meta
%X Self-supervised models have demonstrated remarkable performance in speech processing by learning latent representations from large amounts of unlabeled data. Although these models yield promising results on low-resource languages, the computational expense of fine-tuning all model parameters is prohibitively high. Adapters offer a solution by incorporating lightweight bottleneck structures into pre-trained models, enabling efficient parameter adaptation for downstream tasks. However, randomly initialized adapters often underperform in low-resource scenarios, limiting their applicability in low-resource languages. To address this issue, we develop the Meta-Adapter for self-supervised models to obtain meta-initialized parameters that facilitate quick adaptation to low-resource languages. Extensive experiments on the Common Voice and FLEURS datasets demonstrate the superior performance of Meta-Adapters on 12 low-resource languages spanning four different language families. Moreover, Meta-adapters show better generalization and extensibility than traditional pretraining methods.
%U https://aclanthology.org/2024.lrec-main.979
%P 11215-11221
Markdown (Informal)
[Meta-Adapter for Self-Supervised Speech Models: A Solution to Low-Resource Speech Recognition Challenges](https://aclanthology.org/2024.lrec-main.979) (Chen et al., LREC-COLING 2024)
ACL
