@inproceedings{lijinlong-etal-2025-self,
title = "Self-Supervised Contrastive Learning for Content-Centric Speech Representation",
author = "Lijinlong, Lijinlong and
Dong, Ling and
Wang, Wenjun and
Yu, Zhengtao and
Gao, Shengxiang",
editor = "Sun, Maosong and
Duan, Peiyong and
Liu, Zhiyuan and
Xu, Ruifeng and
Sun, Weiwei",
booktitle = "Proceedings of the 24th {C}hina National Conference on Computational Linguistics ({CCL} 2025)",
month = aug,
year = "2025",
address = "Jinan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2025.ccl-1.61/",
pages = "807--817",
abstract = "``Self-supervised learning (SSL) speech models have achieved remarkable performance across various tasks, with the learned representations often exhibiting a high degree of generality and applicability to multiple downstream tasks. However, these representations contain both speech content and some paralinguistic information, which may be redundant for content-focused tasks.Decoupling this redundant information is challenging. To address this issue, we propose a Self-Supervised Contrastive Representation Learning method (SSCRL), which effectively disentangles paralinguistic information from speech content by aligning similar content speech representations in the feature space using self-supervised contrastive learning with pitch perturbation and speaker perturbation features. Experimental results demonstrate that the proposed method, when fine-tuned on the LibriSpeech 100-hour dataset, achieves superior performance across all content-related tasks in the SUPERB Benchmark, generally outperforming prior approaches.''"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lijinlong-etal-2025-self">
<titleInfo>
<title>Self-Supervised Contrastive Learning for Content-Centric Speech Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lijinlong</namePart>
<namePart type="family">Lijinlong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ling</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengtao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengxiang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiyong</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</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">Weiwei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Jinan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Self-supervised learning (SSL) speech models have achieved remarkable performance across various tasks, with the learned representations often exhibiting a high degree of generality and applicability to multiple downstream tasks. However, these representations contain both speech content and some paralinguistic information, which may be redundant for content-focused tasks.Decoupling this redundant information is challenging. To address this issue, we propose a Self-Supervised Contrastive Representation Learning method (SSCRL), which effectively disentangles paralinguistic information from speech content by aligning similar content speech representations in the feature space using self-supervised contrastive learning with pitch perturbation and speaker perturbation features. Experimental results demonstrate that the proposed method, when fine-tuned on the LibriSpeech 100-hour dataset, achieves superior performance across all content-related tasks in the SUPERB Benchmark, generally outperforming prior approaches.”</abstract>
<identifier type="citekey">lijinlong-etal-2025-self</identifier>
<location>
<url>https://aclanthology.org/2025.ccl-1.61/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>807</start>
<end>817</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Supervised Contrastive Learning for Content-Centric Speech Representation
%A Lijinlong, Lijinlong
%A Dong, Ling
%A Wang, Wenjun
%A Yu, Zhengtao
%A Gao, Shengxiang
%Y Sun, Maosong
%Y Duan, Peiyong
%Y Liu, Zhiyuan
%Y Xu, Ruifeng
%Y Sun, Weiwei
%S Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)
%D 2025
%8 August
%I Chinese Information Processing Society of China
%C Jinan, China
%F lijinlong-etal-2025-self
%X “Self-supervised learning (SSL) speech models have achieved remarkable performance across various tasks, with the learned representations often exhibiting a high degree of generality and applicability to multiple downstream tasks. However, these representations contain both speech content and some paralinguistic information, which may be redundant for content-focused tasks.Decoupling this redundant information is challenging. To address this issue, we propose a Self-Supervised Contrastive Representation Learning method (SSCRL), which effectively disentangles paralinguistic information from speech content by aligning similar content speech representations in the feature space using self-supervised contrastive learning with pitch perturbation and speaker perturbation features. Experimental results demonstrate that the proposed method, when fine-tuned on the LibriSpeech 100-hour dataset, achieves superior performance across all content-related tasks in the SUPERB Benchmark, generally outperforming prior approaches.”
%U https://aclanthology.org/2025.ccl-1.61/
%P 807-817
Markdown (Informal)
[Self-Supervised Contrastive Learning for Content-Centric Speech Representation](https://aclanthology.org/2025.ccl-1.61/) (Lijinlong et al., CCL 2025)
ACL