{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P6KKJNNE7DPW6A3NXUOK3CRNFH","short_pith_number":"pith:P6KKJNNE","schema_version":"1.0","canonical_sha256":"7f94a4b5a4f8df6f036dbd1cad8a2d29fb0cc3d413f84e8b7b37d7b71b53ae43","source":{"kind":"arxiv","id":"2506.01458","version":1},"attestation_state":"computed","paper":{"title":"TalTech Systems for the Interspeech 2025 ML-SUPERB 2.0 Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Artem Fedorchenko, Tanel Alum\\\"ae","submitted_at":"2025-06-02T09:16:09Z","abstract_excerpt":"This paper describes the language identification and multilingual speech recognition system developed at Tallinn University of Technology for the Interspeech 2025 ML-SUPERB 2.0 Challenge. A hybrid language identification system is used, consisting of a pretrained language embedding model and a light-weight speech recognition model with a shared encoder across languages and language-specific bigram language models. For speech recognition, three models are used, where only a single model is applied for each language, depending on the training data availability and performance on held-out data. T"},"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":"2506.01458","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T09:16:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"71e40e95ee9a0e0bbbf4d45d6ea7ae9ce6f583eb14455524af25944c60f67cdd","abstract_canon_sha256":"8053ed88abb699df6285430272f988319136a3cd97eb88fafe511a3896247ba1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:13.907074Z","signature_b64":"Ey38O3+3qycB9AQdROEVqAsmC78cJ0kSAkI6DMNmesIZSaTgqmj7njquGRAjmU410B759WF+jKErl5OQfrwzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f94a4b5a4f8df6f036dbd1cad8a2d29fb0cc3d413f84e8b7b37d7b71b53ae43","last_reissued_at":"2026-07-05T11:14:13.906627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:13.906627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TalTech Systems for the Interspeech 2025 ML-SUPERB 2.0 Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Artem Fedorchenko, Tanel Alum\\\"ae","submitted_at":"2025-06-02T09:16:09Z","abstract_excerpt":"This paper describes the language identification and multilingual speech recognition system developed at Tallinn University of Technology for the Interspeech 2025 ML-SUPERB 2.0 Challenge. A hybrid language identification system is used, consisting of a pretrained language embedding model and a light-weight speech recognition model with a shared encoder across languages and language-specific bigram language models. For speech recognition, three models are used, where only a single model is applied for each language, depending on the training data availability and performance on held-out data. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01458","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/2506.01458/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":"2506.01458","created_at":"2026-07-05T11:14:13.906690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01458v1","created_at":"2026-07-05T11:14:13.906690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01458","created_at":"2026-07-05T11:14:13.906690+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6KKJNNE7DPW","created_at":"2026-07-05T11:14:13.906690+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6KKJNNE7DPW6A3N","created_at":"2026-07-05T11:14:13.906690+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6KKJNNE","created_at":"2026-07-05T11:14:13.906690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01458","citing_title":"TalTech Systems for the Interspeech 2025 ML-SUPERB 2.0 Challenge","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6KKJNNE7DPW6A3NXUOK3CRNFH","json":"https://pith.science/pith/P6KKJNNE7DPW6A3NXUOK3CRNFH.json","graph_json":"https://pith.science/api/pith-number/P6KKJNNE7DPW6A3NXUOK3CRNFH/graph.json","events_json":"https://pith.science/api/pith-number/P6KKJNNE7DPW6A3NXUOK3CRNFH/events.json","paper":"https://pith.science/paper/P6KKJNNE"},"agent_actions":{"view_html":"https://pith.science/pith/P6KKJNNE7DPW6A3NXUOK3CRNFH","download_json":"https://pith.science/pith/P6KKJNNE7DPW6A3NXUOK3CRNFH.json","view_paper":"https://pith.science/paper/P6KKJNNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01458&json=true","fetch_graph":"https://pith.science/api/pith-number/P6KKJNNE7DPW6A3NXUOK3CRNFH/graph.json","fetch_events":"https://pith.science/api/pith-number/P6KKJNNE7DPW6A3NXUOK3CRNFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6KKJNNE7DPW6A3NXUOK3CRNFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6KKJNNE7DPW6A3NXUOK3CRNFH/action/storage_attestation","attest_author":"https://pith.science/pith/P6KKJNNE7DPW6A3NXUOK3CRNFH/action/author_attestation","sign_citation":"https://pith.science/pith/P6KKJNNE7DPW6A3NXUOK3CRNFH/action/citation_signature","submit_replication":"https://pith.science/pith/P6KKJNNE7DPW6A3NXUOK3CRNFH/action/replication_record"}},"created_at":"2026-07-05T11:14:13.906690+00:00","updated_at":"2026-07-05T11:14:13.906690+00:00"}