{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HQWAPYBA3RT4APIGA2JSAY77TY","short_pith_number":"pith:HQWAPYBA","schema_version":"1.0","canonical_sha256":"3c2c07e020dc67c03d0606932063ff9e3b9c1e08177cb25ce3064df7c491bacb","source":{"kind":"arxiv","id":"2101.09149","version":1},"attestation_state":"computed","paper":{"title":"Streaming Models for Joint Speech Recognition and Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Gollan, Joris Kluivers, Matthias Sperber, Orion Weller","submitted_at":"2021-01-22T15:16:54Z","abstract_excerpt":"Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models have the advantage of including automatic speech recognition output, useful for a variety of practical ST systems that often display transcripts to the user alongside the translations. To bridge this gap, recent work has shown initial progress into the feasibility for end-to-end models to produce both of these outputs. However, all previous work has only lo"},"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":"2101.09149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-22T15:16:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1047765dd086bef87396b2f59b491105f669207dfeb686b09103cacecf1a4149","abstract_canon_sha256":"f145d62137574c0e31eeca177017980cb2a1734bee171c78f1bfc36eff08300f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:54.539737Z","signature_b64":"AC13/k2EVQGto5wrY2DrXEQ7YxE6KHCLNRG7ECqV0rSmtPWIM0lGOewO+XmclYotqwq1CYPoToPvPQTgwG5dBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c2c07e020dc67c03d0606932063ff9e3b9c1e08177cb25ce3064df7c491bacb","last_reissued_at":"2026-07-05T02:08:54.539396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:54.539396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Models for Joint Speech Recognition and Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Gollan, Joris Kluivers, Matthias Sperber, Orion Weller","submitted_at":"2021-01-22T15:16:54Z","abstract_excerpt":"Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models have the advantage of including automatic speech recognition output, useful for a variety of practical ST systems that often display transcripts to the user alongside the translations. To bridge this gap, recent work has shown initial progress into the feasibility for end-to-end models to produce both of these outputs. However, all previous work has only lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09149","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/2101.09149/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":"2101.09149","created_at":"2026-07-05T02:08:54.539452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.09149v1","created_at":"2026-07-05T02:08:54.539452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09149","created_at":"2026-07-05T02:08:54.539452+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQWAPYBA3RT4","created_at":"2026-07-05T02:08:54.539452+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQWAPYBA3RT4APIG","created_at":"2026-07-05T02:08:54.539452+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQWAPYBA","created_at":"2026-07-05T02:08:54.539452+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/HQWAPYBA3RT4APIGA2JSAY77TY","json":"https://pith.science/pith/HQWAPYBA3RT4APIGA2JSAY77TY.json","graph_json":"https://pith.science/api/pith-number/HQWAPYBA3RT4APIGA2JSAY77TY/graph.json","events_json":"https://pith.science/api/pith-number/HQWAPYBA3RT4APIGA2JSAY77TY/events.json","paper":"https://pith.science/paper/HQWAPYBA"},"agent_actions":{"view_html":"https://pith.science/pith/HQWAPYBA3RT4APIGA2JSAY77TY","download_json":"https://pith.science/pith/HQWAPYBA3RT4APIGA2JSAY77TY.json","view_paper":"https://pith.science/paper/HQWAPYBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.09149&json=true","fetch_graph":"https://pith.science/api/pith-number/HQWAPYBA3RT4APIGA2JSAY77TY/graph.json","fetch_events":"https://pith.science/api/pith-number/HQWAPYBA3RT4APIGA2JSAY77TY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQWAPYBA3RT4APIGA2JSAY77TY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQWAPYBA3RT4APIGA2JSAY77TY/action/storage_attestation","attest_author":"https://pith.science/pith/HQWAPYBA3RT4APIGA2JSAY77TY/action/author_attestation","sign_citation":"https://pith.science/pith/HQWAPYBA3RT4APIGA2JSAY77TY/action/citation_signature","submit_replication":"https://pith.science/pith/HQWAPYBA3RT4APIGA2JSAY77TY/action/replication_record"}},"created_at":"2026-07-05T02:08:54.539452+00:00","updated_at":"2026-07-05T02:08:54.539452+00:00"}