{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XQQG3DMEQJ72AZWP7YSPUOM2YT","short_pith_number":"pith:XQQG3DME","schema_version":"1.0","canonical_sha256":"bc206d8d84827fa066cffe24fa399ac4ff474def11ceed91524f52e128707f20","source":{"kind":"arxiv","id":"2409.06372","version":1},"attestation_state":"computed","paper":{"title":"SpeechTaxi: On Multilingual Semantic Speech Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Goran Glava\\v{s}, Lennart Keller","submitted_at":"2024-09-10T09:56:15Z","abstract_excerpt":"Recent advancements in multilingual speech encoding as well as transcription raise the question of the most effective approach to semantic speech classification. Concretely, can (1) end-to-end (E2E) classifiers obtained by fine-tuning state-of-the-art multilingual speech encoders (MSEs) match or surpass the performance of (2) cascading (CA), where speech is first transcribed into text and classification is delegated to a text-based classifier. To answer this, we first construct SpeechTaxi, an 80-hour multilingual dataset for semantic speech classification of Bible verses, covering 28 diverse l"},"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":"2409.06372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T09:56:15Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bd0edff8f1906f1bd6cc1bff16dbda00b74c9f03e623f648a2fe11e16cd71a21","abstract_canon_sha256":"c067be86ac33f7301469b44b1af8082659ded7333bceeab551cabd56edf1f721"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:23.559572Z","signature_b64":"HYhqgC5RYMa6Ku94XdO7asP0yoBLpLgHC8BpbM+9kj1IffAupfvdymJGjA2+lMqFCwZ9iyiznD/1SrOhEeIEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc206d8d84827fa066cffe24fa399ac4ff474def11ceed91524f52e128707f20","last_reissued_at":"2026-07-05T09:05:23.559197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:23.559197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechTaxi: On Multilingual Semantic Speech Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Goran Glava\\v{s}, Lennart Keller","submitted_at":"2024-09-10T09:56:15Z","abstract_excerpt":"Recent advancements in multilingual speech encoding as well as transcription raise the question of the most effective approach to semantic speech classification. Concretely, can (1) end-to-end (E2E) classifiers obtained by fine-tuning state-of-the-art multilingual speech encoders (MSEs) match or surpass the performance of (2) cascading (CA), where speech is first transcribed into text and classification is delegated to a text-based classifier. To answer this, we first construct SpeechTaxi, an 80-hour multilingual dataset for semantic speech classification of Bible verses, covering 28 diverse l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06372","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/2409.06372/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":"2409.06372","created_at":"2026-07-05T09:05:23.559255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06372v1","created_at":"2026-07-05T09:05:23.559255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06372","created_at":"2026-07-05T09:05:23.559255+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQQG3DMEQJ72","created_at":"2026-07-05T09:05:23.559255+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQQG3DMEQJ72AZWP","created_at":"2026-07-05T09:05:23.559255+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQQG3DME","created_at":"2026-07-05T09:05:23.559255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06117","citing_title":"Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQQG3DMEQJ72AZWP7YSPUOM2YT","json":"https://pith.science/pith/XQQG3DMEQJ72AZWP7YSPUOM2YT.json","graph_json":"https://pith.science/api/pith-number/XQQG3DMEQJ72AZWP7YSPUOM2YT/graph.json","events_json":"https://pith.science/api/pith-number/XQQG3DMEQJ72AZWP7YSPUOM2YT/events.json","paper":"https://pith.science/paper/XQQG3DME"},"agent_actions":{"view_html":"https://pith.science/pith/XQQG3DMEQJ72AZWP7YSPUOM2YT","download_json":"https://pith.science/pith/XQQG3DMEQJ72AZWP7YSPUOM2YT.json","view_paper":"https://pith.science/paper/XQQG3DME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06372&json=true","fetch_graph":"https://pith.science/api/pith-number/XQQG3DMEQJ72AZWP7YSPUOM2YT/graph.json","fetch_events":"https://pith.science/api/pith-number/XQQG3DMEQJ72AZWP7YSPUOM2YT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQQG3DMEQJ72AZWP7YSPUOM2YT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQQG3DMEQJ72AZWP7YSPUOM2YT/action/storage_attestation","attest_author":"https://pith.science/pith/XQQG3DMEQJ72AZWP7YSPUOM2YT/action/author_attestation","sign_citation":"https://pith.science/pith/XQQG3DMEQJ72AZWP7YSPUOM2YT/action/citation_signature","submit_replication":"https://pith.science/pith/XQQG3DMEQJ72AZWP7YSPUOM2YT/action/replication_record"}},"created_at":"2026-07-05T09:05:23.559255+00:00","updated_at":"2026-07-05T09:05:23.559255+00:00"}