{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CSALTPIHNOKE3MO4IXJ2FS62LQ","short_pith_number":"pith:CSALTPIH","schema_version":"1.0","canonical_sha256":"1480b9bd076b944db1dc45d3a2cbda5c38a6b815b6e18a84273b4058d4a62b65","source":{"kind":"arxiv","id":"2011.06226","version":1},"attestation_state":"computed","paper":{"title":"Cross-lingual and Multilingual Spoken Term Detection for Low-Resource Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sanket Shah, Satarupa Guha, Simran Khanuja, Sunayana Sitaram","submitted_at":"2020-11-12T06:41:27Z","abstract_excerpt":"Spoken Term Detection (STD) is the task of searching for words or phrases within audio, given either text or spoken input as a query. In this work, we use state-of-the-art Hindi, Tamil and Telugu ASR systems cross-lingually for lexical Spoken Term Detection in ten low-resource Indian languages. Since no publicly available dataset exists for Spoken Term Detection in these languages, we create a new dataset using a publicly available TTS dataset. We report a standard metric for STD, Mean Term Weighted Value (MTWV) and show that ASR systems built in languages that are phonetically similar to the "},"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":"2011.06226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-12T06:41:27Z","cross_cats_sorted":[],"title_canon_sha256":"4f59a825008e1818987757070e702660a18c53d02b5f0c0bf59aad844d51c264","abstract_canon_sha256":"7affc77c36414491d855dfa6ceee7ea1e46745bcb1de390b1ecc8b382cb0a889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:13.286119Z","signature_b64":"I6yslyO3jGu9xHdSZn5+0HDvItKWhBFKc/by5ytPxLNHMcIA7vFsTLPRB/0NLQya2imveH4fdu5dP+Gc8WXVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1480b9bd076b944db1dc45d3a2cbda5c38a6b815b6e18a84273b4058d4a62b65","last_reissued_at":"2026-07-05T01:51:13.285734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:13.285734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-lingual and Multilingual Spoken Term Detection for Low-Resource Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sanket Shah, Satarupa Guha, Simran Khanuja, Sunayana Sitaram","submitted_at":"2020-11-12T06:41:27Z","abstract_excerpt":"Spoken Term Detection (STD) is the task of searching for words or phrases within audio, given either text or spoken input as a query. In this work, we use state-of-the-art Hindi, Tamil and Telugu ASR systems cross-lingually for lexical Spoken Term Detection in ten low-resource Indian languages. Since no publicly available dataset exists for Spoken Term Detection in these languages, we create a new dataset using a publicly available TTS dataset. We report a standard metric for STD, Mean Term Weighted Value (MTWV) and show that ASR systems built in languages that are phonetically similar to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06226","kind":"arxiv","version":1},"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/2011.06226/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":"2011.06226","created_at":"2026-07-05T01:51:13.285788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.06226v1","created_at":"2026-07-05T01:51:13.285788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06226","created_at":"2026-07-05T01:51:13.285788+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSALTPIHNOKE","created_at":"2026-07-05T01:51:13.285788+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSALTPIHNOKE3MO4","created_at":"2026-07-05T01:51:13.285788+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSALTPIH","created_at":"2026-07-05T01:51:13.285788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ","json":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ.json","graph_json":"https://pith.science/api/pith-number/CSALTPIHNOKE3MO4IXJ2FS62LQ/graph.json","events_json":"https://pith.science/api/pith-number/CSALTPIHNOKE3MO4IXJ2FS62LQ/events.json","paper":"https://pith.science/paper/CSALTPIH"},"agent_actions":{"view_html":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ","download_json":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ.json","view_paper":"https://pith.science/paper/CSALTPIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.06226&json=true","fetch_graph":"https://pith.science/api/pith-number/CSALTPIHNOKE3MO4IXJ2FS62LQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CSALTPIHNOKE3MO4IXJ2FS62LQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/action/storage_attestation","attest_author":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/action/author_attestation","sign_citation":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/action/citation_signature","submit_replication":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/action/replication_record"}},"created_at":"2026-07-05T01:51:13.285788+00:00","updated_at":"2026-07-05T01:51:13.285788+00:00"}