{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FAV3ZOBX72RT67WPQR5LDH23FA","short_pith_number":"pith:FAV3ZOBX","schema_version":"1.0","canonical_sha256":"282bbcb837fea33f7ecf847ab19f5b2830172cade401a1c612ad0fec94331d4a","source":{"kind":"arxiv","id":"2506.02157","version":1},"attestation_state":"computed","paper":{"title":"HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Amir Hussein, Cihan Xiao, Dan Povey, Leibny Paola Garcia, Matthew Wiesner, Sanjeev Khudanpur","submitted_at":"2025-06-02T18:37:50Z","abstract_excerpt":"Neural transducers (NT) provide an effective framework for speech streaming, demonstrating strong performance in automatic speech recognition (ASR). However, the application of NT to speech translation (ST) remains challenging, as existing approaches struggle with word reordering and performance degradation when jointly modeling ASR and ST, resulting in a gap with attention-based encoder-decoder (AED) models. Existing NT-based ST approaches also suffer from high computational training costs. To address these issues, we propose HENT-SRT (Hierarchical Efficient Neural Transducer for Speech Recog"},"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":"2506.02157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T18:37:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"517ce56308b22415debd632f8b7d3aa78ceba86a84c8b658e9596a76d04464da","abstract_canon_sha256":"7ffdbe79b7ddafe7478f9f67091a89fc4d20d4aec977e4a5ccd2a11cd49d5c1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:33.490367Z","signature_b64":"/S3xeerWUqBBVBlOPHdk8JuxXTvAINUZ2O+GHH2vsZUejEB3HWivQ3Dr/pnVLdqsukrT0WLRR6BW30Ff8d7YBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"282bbcb837fea33f7ecf847ab19f5b2830172cade401a1c612ad0fec94331d4a","last_reissued_at":"2026-07-05T11:14:33.489891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:33.489891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Amir Hussein, Cihan Xiao, Dan Povey, Leibny Paola Garcia, Matthew Wiesner, Sanjeev Khudanpur","submitted_at":"2025-06-02T18:37:50Z","abstract_excerpt":"Neural transducers (NT) provide an effective framework for speech streaming, demonstrating strong performance in automatic speech recognition (ASR). However, the application of NT to speech translation (ST) remains challenging, as existing approaches struggle with word reordering and performance degradation when jointly modeling ASR and ST, resulting in a gap with attention-based encoder-decoder (AED) models. Existing NT-based ST approaches also suffer from high computational training costs. To address these issues, we propose HENT-SRT (Hierarchical Efficient Neural Transducer for Speech Recog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02157","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/2506.02157/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":"2506.02157","created_at":"2026-07-05T11:14:33.489949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02157v1","created_at":"2026-07-05T11:14:33.489949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02157","created_at":"2026-07-05T11:14:33.489949+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAV3ZOBX72RT","created_at":"2026-07-05T11:14:33.489949+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAV3ZOBX72RT67WP","created_at":"2026-07-05T11:14:33.489949+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAV3ZOBX","created_at":"2026-07-05T11:14:33.489949+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/FAV3ZOBX72RT67WPQR5LDH23FA","json":"https://pith.science/pith/FAV3ZOBX72RT67WPQR5LDH23FA.json","graph_json":"https://pith.science/api/pith-number/FAV3ZOBX72RT67WPQR5LDH23FA/graph.json","events_json":"https://pith.science/api/pith-number/FAV3ZOBX72RT67WPQR5LDH23FA/events.json","paper":"https://pith.science/paper/FAV3ZOBX"},"agent_actions":{"view_html":"https://pith.science/pith/FAV3ZOBX72RT67WPQR5LDH23FA","download_json":"https://pith.science/pith/FAV3ZOBX72RT67WPQR5LDH23FA.json","view_paper":"https://pith.science/paper/FAV3ZOBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02157&json=true","fetch_graph":"https://pith.science/api/pith-number/FAV3ZOBX72RT67WPQR5LDH23FA/graph.json","fetch_events":"https://pith.science/api/pith-number/FAV3ZOBX72RT67WPQR5LDH23FA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAV3ZOBX72RT67WPQR5LDH23FA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAV3ZOBX72RT67WPQR5LDH23FA/action/storage_attestation","attest_author":"https://pith.science/pith/FAV3ZOBX72RT67WPQR5LDH23FA/action/author_attestation","sign_citation":"https://pith.science/pith/FAV3ZOBX72RT67WPQR5LDH23FA/action/citation_signature","submit_replication":"https://pith.science/pith/FAV3ZOBX72RT67WPQR5LDH23FA/action/replication_record"}},"created_at":"2026-07-05T11:14:33.489949+00:00","updated_at":"2026-07-05T11:14:33.489949+00:00"}