{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/153784"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/153784","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Perturbation-invariant Speech Representation Learning by Online Clustering","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_html":"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_has_math":false,"creators":["Chang, Heng-Jui"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Glass, James R."],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-02","date_published":"2024-02","updated_at":"2026-07-22T22:20:44Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/153784","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Glass, James R."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Chang, Heng-Jui"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-03-15T19:23:50Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-03-15T19:23:50Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-02"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Science in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/153784"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Perturbation-invariant Speech Representation Learning by Online Clustering"]}]}],"canonical_facts":{"dc:contributor.advisor":["Glass, James R."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Chang, Heng-Jui"],"dc:date.accessioned":["2024-03-15T19:23:50Z"],"dc:date.available":["2024-03-15T19:23:50Z"],"dc:date.issued":["2024-02"],"dc:description.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."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/153784"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Perturbation-invariant Speech Representation Learning by Online Clustering"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:20:44Z"}