<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2022-self">
    <titleInfo>
        <title>Self-supervised Rewiring of Pre-trained Speech Encoders:Towards Faster Fine-tuning with Less Labels in Speech Processing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinming</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gholamreza</namePart>
        <namePart type="family">Haffari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ehsan</namePart>
        <namePart type="family">Shareghi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve state-of-the-art. In text domain this has been partly attributed to sub-optimality of the representation space in pre-trained Transformers. In this work, we take a sober look into pre-trained speech encoders and rewire their representation space without requiring any task-specific labels. Our method utilises neutrally synthesised version of audio inputs along with frame masking to construct positive pairs for contrastive self-supervised learning. When used for augmenting the wav2vec 2 encoder, we observe consistent improvement of isotropy in the representation space. Our experiments on 6 speech processing tasks, exhibit a significant convergence speedup during task fine-tuning as well as consistent task improvement, specially in low-resource settings.</abstract>
    <identifier type="citekey">yang-etal-2022-self</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.141</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.141</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>1952</start>
            <end>1959</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-supervised Rewiring of Pre-trained Speech Encoders:Towards Faster Fine-tuning with Less Labels in Speech Processing
%A Yang, Hao
%A Zhao, Jinming
%A Haffari, Gholamreza
%A Shareghi, Ehsan
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F yang-etal-2022-self
%X Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve state-of-the-art. In text domain this has been partly attributed to sub-optimality of the representation space in pre-trained Transformers. In this work, we take a sober look into pre-trained speech encoders and rewire their representation space without requiring any task-specific labels. Our method utilises neutrally synthesised version of audio inputs along with frame masking to construct positive pairs for contrastive self-supervised learning. When used for augmenting the wav2vec 2 encoder, we observe consistent improvement of isotropy in the representation space. Our experiments on 6 speech processing tasks, exhibit a significant convergence speedup during task fine-tuning as well as consistent task improvement, specially in low-resource settings.
%R 10.18653/v1/2022.findings-emnlp.141
%U https://aclanthology.org/2022.findings-emnlp.141
%U https://doi.org/10.18653/v1/2022.findings-emnlp.141
%P 1952-1959

Markdown (Informal)

[Self-supervised Rewiring of Pre-trained Speech Encoders:Towards Faster Fine-tuning with Less Labels in Speech Processing](https://aclanthology.org/2022.findings-emnlp.141) (Yang et al., Findings 2022)

• Self-supervised Rewiring of Pre-trained Speech Encoders:Towards Faster Fine-tuning with Less Labels in Speech Processing (Yang et al., Findings 2022)

ACL

• Hao Yang, Jinming Zhao, Gholamreza Haffari, and Ehsan Shareghi. 2022. Self-supervised Rewiring of Pre-trained Speech Encoders:Towards Faster Fine-tuning with Less Labels in Speech Processing. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1952–1959, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.