{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NML4NKJS2E3IN34I5XCUXLPKS2","short_pith_number":"pith:NML4NKJS","schema_version":"1.0","canonical_sha256":"6b17c6a932d13686ef88edc54badea96ab326ef5193082acaedb66e859999f51","source":{"kind":"arxiv","id":"2402.01828","version":1},"attestation_state":"computed","paper":{"title":"Retrieval Augmented End-to-End Spoken Dialog Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dian Yu, Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang, Wei Han, Yuan Cao","submitted_at":"2024-02-02T18:23:09Z","abstract_excerpt":"We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context learning capability intrinsic to the pretrained LLM. In this paper, we apply SLM to speech dialog applications where the dialog states are inferred directly from the audio signal.\n  Task-oriented dialogs often contain domain-specific entities, i.e., restaurants, hotels, train stations, and city names, which are difficult to recognize, however, critical for the downstream applications. Inspired by the RAG (retrieval-au"},"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":"2402.01828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:09Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"145d06f4bf585624fc84500cf3bfe37f39831c079dccacb958bc5d184e0a088a","abstract_canon_sha256":"73a2c7b02adaf14e40894d0d61b8ab5a4143c75183d2a3ce497542a200905e79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:24.093018Z","signature_b64":"HeCNj2/RRD6vXbzTWmFAw0j2SJUke93zn1XUa9siQVsQ47ppu9ZpmTo9hEQY7I5sXr1dAEN3BEAqce1gh5EOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b17c6a932d13686ef88edc54badea96ab326ef5193082acaedb66e859999f51","last_reissued_at":"2026-07-05T07:42:24.092538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:24.092538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval Augmented End-to-End Spoken Dialog Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dian Yu, Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang, Wei Han, Yuan Cao","submitted_at":"2024-02-02T18:23:09Z","abstract_excerpt":"We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context learning capability intrinsic to the pretrained LLM. In this paper, we apply SLM to speech dialog applications where the dialog states are inferred directly from the audio signal.\n  Task-oriented dialogs often contain domain-specific entities, i.e., restaurants, hotels, train stations, and city names, which are difficult to recognize, however, critical for the downstream applications. Inspired by the RAG (retrieval-au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01828","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/2402.01828/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":"2402.01828","created_at":"2026-07-05T07:42:24.092598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01828v1","created_at":"2026-07-05T07:42:24.092598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01828","created_at":"2026-07-05T07:42:24.092598+00:00"},{"alias_kind":"pith_short_12","alias_value":"NML4NKJS2E3I","created_at":"2026-07-05T07:42:24.092598+00:00"},{"alias_kind":"pith_short_16","alias_value":"NML4NKJS2E3IN34I","created_at":"2026-07-05T07:42:24.092598+00:00"},{"alias_kind":"pith_short_8","alias_value":"NML4NKJS","created_at":"2026-07-05T07:42:24.092598+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/NML4NKJS2E3IN34I5XCUXLPKS2","json":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2.json","graph_json":"https://pith.science/api/pith-number/NML4NKJS2E3IN34I5XCUXLPKS2/graph.json","events_json":"https://pith.science/api/pith-number/NML4NKJS2E3IN34I5XCUXLPKS2/events.json","paper":"https://pith.science/paper/NML4NKJS"},"agent_actions":{"view_html":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2","download_json":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2.json","view_paper":"https://pith.science/paper/NML4NKJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01828&json=true","fetch_graph":"https://pith.science/api/pith-number/NML4NKJS2E3IN34I5XCUXLPKS2/graph.json","fetch_events":"https://pith.science/api/pith-number/NML4NKJS2E3IN34I5XCUXLPKS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2/action/storage_attestation","attest_author":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2/action/author_attestation","sign_citation":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2/action/citation_signature","submit_replication":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2/action/replication_record"}},"created_at":"2026-07-05T07:42:24.092598+00:00","updated_at":"2026-07-05T07:42:24.092598+00:00"}