{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7EKQIRJC6G57KBC4I6TOTFQDJN","short_pith_number":"pith:7EKQIRJC","schema_version":"1.0","canonical_sha256":"f915044522f1bbf5045c47a6e996034b53ce76f207297bc265e427d8df7e0060","source":{"kind":"arxiv","id":"2309.17020","version":2},"attestation_state":"computed","paper":{"title":"Low-Resource Self-Supervised Learning with SSL-Enhanced TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdelrahman Mohamed, Ali Elkahky, Emmanuel Dupoux, Hung-yi Lee, Jade Copet, Po-chun Hsu, Tu Anh Nguyen, Wei-Ning Hsu, Yossi Adi","submitted_at":"2023-09-29T07:09:23Z","abstract_excerpt":"Self-supervised learning (SSL) techniques have achieved remarkable results in various speech processing tasks. Nonetheless, a significant challenge remains in reducing the reliance on vast amounts of speech data for pre-training. This paper proposes to address this challenge by leveraging synthetic speech to augment a low-resource pre-training corpus. We construct a high-quality text-to-speech (TTS) system with limited resources using SSL features and generate a large synthetic corpus for pre-training. Experimental results demonstrate that our proposed approach effectively reduces the demand f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.17020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-29T07:09:23Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"52de4ecd4a3ca9f8aa0e816a3b479e0f7da35f3ef1eef55da9c4bef339d07bee","abstract_canon_sha256":"b3cca9fbc6558b02f8eb3cecb947a607c8996c2b98e5d207a283f5635e312d2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:59.136061Z","signature_b64":"50a+e8+N13JQIcZL5ICkNjLmP9KZqGwlevpmcosJCSWju0W+Wh/3jGl44OiPV0awmwxBVTS7KRy2tdiK9gnGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f915044522f1bbf5045c47a6e996034b53ce76f207297bc265e427d8df7e0060","last_reissued_at":"2026-07-05T08:26:59.135565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:59.135565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Resource Self-Supervised Learning with SSL-Enhanced TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdelrahman Mohamed, Ali Elkahky, Emmanuel Dupoux, Hung-yi Lee, Jade Copet, Po-chun Hsu, Tu Anh Nguyen, Wei-Ning Hsu, Yossi Adi","submitted_at":"2023-09-29T07:09:23Z","abstract_excerpt":"Self-supervised learning (SSL) techniques have achieved remarkable results in various speech processing tasks. Nonetheless, a significant challenge remains in reducing the reliance on vast amounts of speech data for pre-training. This paper proposes to address this challenge by leveraging synthetic speech to augment a low-resource pre-training corpus. We construct a high-quality text-to-speech (TTS) system with limited resources using SSL features and generate a large synthetic corpus for pre-training. Experimental results demonstrate that our proposed approach effectively reduces the demand f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17020","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.17020/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.17020","created_at":"2026-07-05T08:26:59.135635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17020v2","created_at":"2026-07-05T08:26:59.135635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17020","created_at":"2026-07-05T08:26:59.135635+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EKQIRJC6G57","created_at":"2026-07-05T08:26:59.135635+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EKQIRJC6G57KBC4","created_at":"2026-07-05T08:26:59.135635+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EKQIRJC","created_at":"2026-07-05T08:26:59.135635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05056","citing_title":"Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EKQIRJC6G57KBC4I6TOTFQDJN","json":"https://pith.science/pith/7EKQIRJC6G57KBC4I6TOTFQDJN.json","graph_json":"https://pith.science/api/pith-number/7EKQIRJC6G57KBC4I6TOTFQDJN/graph.json","events_json":"https://pith.science/api/pith-number/7EKQIRJC6G57KBC4I6TOTFQDJN/events.json","paper":"https://pith.science/paper/7EKQIRJC"},"agent_actions":{"view_html":"https://pith.science/pith/7EKQIRJC6G57KBC4I6TOTFQDJN","download_json":"https://pith.science/pith/7EKQIRJC6G57KBC4I6TOTFQDJN.json","view_paper":"https://pith.science/paper/7EKQIRJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17020&json=true","fetch_graph":"https://pith.science/api/pith-number/7EKQIRJC6G57KBC4I6TOTFQDJN/graph.json","fetch_events":"https://pith.science/api/pith-number/7EKQIRJC6G57KBC4I6TOTFQDJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EKQIRJC6G57KBC4I6TOTFQDJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EKQIRJC6G57KBC4I6TOTFQDJN/action/storage_attestation","attest_author":"https://pith.science/pith/7EKQIRJC6G57KBC4I6TOTFQDJN/action/author_attestation","sign_citation":"https://pith.science/pith/7EKQIRJC6G57KBC4I6TOTFQDJN/action/citation_signature","submit_replication":"https://pith.science/pith/7EKQIRJC6G57KBC4I6TOTFQDJN/action/replication_record"}},"created_at":"2026-07-05T08:26:59.135635+00:00","updated_at":"2026-07-05T08:26:59.135635+00:00"}