{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VWI2SYO2F4BFHZYWHUXP2LBOQN","short_pith_number":"pith:VWI2SYO2","schema_version":"1.0","canonical_sha256":"ad91a961da2f0253e7163d2efd2c2e83589a19d784e12ac9ad052a4356b9207d","source":{"kind":"arxiv","id":"2203.16973","version":4},"attestation_state":"computed","paper":{"title":"Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ashish Seth, Lodagala V S V Durga Prasad, Sreyan Ghosh, S. Umesh","submitted_at":"2022-03-31T11:48:24Z","abstract_excerpt":"Self-supervised learning (SSL) to learn high-level speech representations has been a popular approach to building Automatic Speech Recognition (ASR) systems in low-resource settings. However, the common assumption made in literature is that a considerable amount of unlabeled data is available for the same domain or language that can be leveraged for SSL pre-training, which we acknowledge is not feasible in a real-world setting. In this paper, as part of the Interspeech Gram Vaani ASR challenge, we try to study the effect of domain, language, dataset size, and other aspects of our upstream pre-"},"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":"2203.16973","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-31T11:48:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"08217cd4996dfa1d803763c07f473b28e1b0cabe1357b91528d072292da8c480","abstract_canon_sha256":"4c3892a2c3bd832d1e8a2cc63eb68e3a30035f2d5ac4032a6eefbb5cd807bf26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:15.475807Z","signature_b64":"GhQ8833kCytykNGvlSWhD5yqh9dnGLiNBpZ8atwce0KUfBd/CE4sJ4T1Cu8OK1BZhF4Hd5/VdRKIfuD1C67PCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad91a961da2f0253e7163d2efd2c2e83589a19d784e12ac9ad052a4356b9207d","last_reissued_at":"2026-07-05T06:11:15.475339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:15.475339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ashish Seth, Lodagala V S V Durga Prasad, Sreyan Ghosh, S. Umesh","submitted_at":"2022-03-31T11:48:24Z","abstract_excerpt":"Self-supervised learning (SSL) to learn high-level speech representations has been a popular approach to building Automatic Speech Recognition (ASR) systems in low-resource settings. However, the common assumption made in literature is that a considerable amount of unlabeled data is available for the same domain or language that can be leveraged for SSL pre-training, which we acknowledge is not feasible in a real-world setting. In this paper, as part of the Interspeech Gram Vaani ASR challenge, we try to study the effect of domain, language, dataset size, and other aspects of our upstream pre-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16973","kind":"arxiv","version":4},"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/2203.16973/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":"2203.16973","created_at":"2026-07-05T06:11:15.475401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16973v4","created_at":"2026-07-05T06:11:15.475401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16973","created_at":"2026-07-05T06:11:15.475401+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWI2SYO2F4BF","created_at":"2026-07-05T06:11:15.475401+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWI2SYO2F4BFHZYW","created_at":"2026-07-05T06:11:15.475401+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWI2SYO2","created_at":"2026-07-05T06:11:15.475401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18217","citing_title":"How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWI2SYO2F4BFHZYWHUXP2LBOQN","json":"https://pith.science/pith/VWI2SYO2F4BFHZYWHUXP2LBOQN.json","graph_json":"https://pith.science/api/pith-number/VWI2SYO2F4BFHZYWHUXP2LBOQN/graph.json","events_json":"https://pith.science/api/pith-number/VWI2SYO2F4BFHZYWHUXP2LBOQN/events.json","paper":"https://pith.science/paper/VWI2SYO2"},"agent_actions":{"view_html":"https://pith.science/pith/VWI2SYO2F4BFHZYWHUXP2LBOQN","download_json":"https://pith.science/pith/VWI2SYO2F4BFHZYWHUXP2LBOQN.json","view_paper":"https://pith.science/paper/VWI2SYO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16973&json=true","fetch_graph":"https://pith.science/api/pith-number/VWI2SYO2F4BFHZYWHUXP2LBOQN/graph.json","fetch_events":"https://pith.science/api/pith-number/VWI2SYO2F4BFHZYWHUXP2LBOQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWI2SYO2F4BFHZYWHUXP2LBOQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWI2SYO2F4BFHZYWHUXP2LBOQN/action/storage_attestation","attest_author":"https://pith.science/pith/VWI2SYO2F4BFHZYWHUXP2LBOQN/action/author_attestation","sign_citation":"https://pith.science/pith/VWI2SYO2F4BFHZYWHUXP2LBOQN/action/citation_signature","submit_replication":"https://pith.science/pith/VWI2SYO2F4BFHZYWHUXP2LBOQN/action/replication_record"}},"created_at":"2026-07-05T06:11:15.475401+00:00","updated_at":"2026-07-05T06:11:15.475401+00:00"}