2026-09-20T23:52:24Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1537842024-03-16T04:08:33Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Glass, James R.
Chang, Heng-Jui
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2024-03-15T19:23:50Z
2024-03-15T19:23:50Z
2024-02
2024-02-21T17:10:05.097Z
https://hdl.handle.net/1721.1/153784
https://orcid.org/0000-0002-1690-2610
Despite success across various tasks, self-supervised speech models face significant challenges in enhancing content-related performance with unlabeled data, requiring substantial computational resources. Meanwhile, learning from clustered discrete units has been shown to facilitate accurate phonetic representations. Thus, this thesis investigates speaker and noise-invariant speech representations. First, Speaker-invariant Clustering (Spin) is proposed to extract content representations through online clustering and speaker-invariant cross-view prediction. Second, Robust Spin (R-Spin) is devised to extend Spin to handle more distorted speech signals by leveraging acoustic pieces. Furthermore, this thesis includes a diverse set of evaluation and visualization techniques to quantitatively and qualitatively analyze the perturbation invariability of the proposed methods. This thesis offers approaches to producing perturbation-invariant speech representations and deeply investigates the characteristics of the learned representations, providing insights into these models and cultivating future extension possibilities.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Perturbation-invariant Speech Representation Learning by Online Clustering
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="01621aeb-f547-4483-9859-fdd7bfd50497">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Perturbation-invariant Speech Representation Learning by Online Clustering</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2024-02</PublicationDate>
<Authors>
<Author>
<DisplayName>Chang, Heng-Jui</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Despite success across various tasks, self-supervised speech models face significant challenges in enhancing content-related performance with unlabeled data, requiring substantial computational resources. Meanwhile, learning from clustered discrete units has been shown to facilitate accurate phonetic representations. Thus, this thesis investigates speaker and noise-invariant speech representations. First, Speaker-invariant Clustering (Spin) is proposed to extract content representations through online clustering and speaker-invariant cross-view prediction. Second, Robust Spin (R-Spin) is devised to extend Spin to handle more distorted speech signals by leveraging acoustic pieces. Furthermore, this thesis includes a diverse set of evaluation and visualization techniques to quantitatively and qualitatively analyze the perturbation invariability of the proposed methods. This thesis offers approaches to producing perturbation-invariant speech representations and deeply investigates the characteristics of the learned representations, providing insights into these models and cultivating future extension possibilities.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>