{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HHMLWHOCA22URWTYFWGKNHPO3R","short_pith_number":"pith:HHMLWHOC","schema_version":"1.0","canonical_sha256":"39d8bb1dc206b548da782d8ca69deedc648da13fe75f18f732ffc0967ba24aa2","source":{"kind":"arxiv","id":"2211.02809","version":3},"attestation_state":"computed","paper":{"title":"LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Eric Sun, Jian Xue, Jinyu Li, Long Zhou, Peidong Wang, Shujie Liu, Yashesh Gaur, Yu Wu","submitted_at":"2022-11-05T04:03:55Z","abstract_excerpt":"Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world applications, such joint ASR and ST models may need to be streaming and do not require source language identification (i.e. language-agnostic). In this paper, we propose LAMASSU, a streaming language-agnostic multilingual speech recognition and translation model using neural transducers. Based on the transducer model structure, we propose four methods, a unified joint and prediction netwo"},"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":"2211.02809","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-05T04:03:55Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"58c61321a14eac066e48f74e13e156cf32a54bdab94db419474613201cea5e3f","abstract_canon_sha256":"9c8d6269bce3434c2db3ec9c09f38c1322fbc08ab7685a92ca3fa5f9097ad148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:47.559531Z","signature_b64":"EN6Vizoh9wfPRHfSPZGdgrOdlGYcsJocxCmgUo8O+2WCQLIWzk8bC4IBO9W39Gubqkvr9Iak066LO6eeOyk2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39d8bb1dc206b548da782d8ca69deedc648da13fe75f18f732ffc0967ba24aa2","last_reissued_at":"2026-07-05T07:02:47.559098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:47.559098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Eric Sun, Jian Xue, Jinyu Li, Long Zhou, Peidong Wang, Shujie Liu, Yashesh Gaur, Yu Wu","submitted_at":"2022-11-05T04:03:55Z","abstract_excerpt":"Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world applications, such joint ASR and ST models may need to be streaming and do not require source language identification (i.e. language-agnostic). In this paper, we propose LAMASSU, a streaming language-agnostic multilingual speech recognition and translation model using neural transducers. Based on the transducer model structure, we propose four methods, a unified joint and prediction netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02809","kind":"arxiv","version":3},"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/2211.02809/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":"2211.02809","created_at":"2026-07-05T07:02:47.559163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02809v3","created_at":"2026-07-05T07:02:47.559163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02809","created_at":"2026-07-05T07:02:47.559163+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHMLWHOCA22U","created_at":"2026-07-05T07:02:47.559163+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHMLWHOCA22URWTY","created_at":"2026-07-05T07:02:47.559163+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHMLWHOC","created_at":"2026-07-05T07:02:47.559163+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/HHMLWHOCA22URWTYFWGKNHPO3R","json":"https://pith.science/pith/HHMLWHOCA22URWTYFWGKNHPO3R.json","graph_json":"https://pith.science/api/pith-number/HHMLWHOCA22URWTYFWGKNHPO3R/graph.json","events_json":"https://pith.science/api/pith-number/HHMLWHOCA22URWTYFWGKNHPO3R/events.json","paper":"https://pith.science/paper/HHMLWHOC"},"agent_actions":{"view_html":"https://pith.science/pith/HHMLWHOCA22URWTYFWGKNHPO3R","download_json":"https://pith.science/pith/HHMLWHOCA22URWTYFWGKNHPO3R.json","view_paper":"https://pith.science/paper/HHMLWHOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02809&json=true","fetch_graph":"https://pith.science/api/pith-number/HHMLWHOCA22URWTYFWGKNHPO3R/graph.json","fetch_events":"https://pith.science/api/pith-number/HHMLWHOCA22URWTYFWGKNHPO3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHMLWHOCA22URWTYFWGKNHPO3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHMLWHOCA22URWTYFWGKNHPO3R/action/storage_attestation","attest_author":"https://pith.science/pith/HHMLWHOCA22URWTYFWGKNHPO3R/action/author_attestation","sign_citation":"https://pith.science/pith/HHMLWHOCA22URWTYFWGKNHPO3R/action/citation_signature","submit_replication":"https://pith.science/pith/HHMLWHOCA22URWTYFWGKNHPO3R/action/replication_record"}},"created_at":"2026-07-05T07:02:47.559163+00:00","updated_at":"2026-07-05T07:02:47.559163+00:00"}