{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DWXAVE7LTS4AUE3Y2YC5KZ42J3","short_pith_number":"pith:DWXAVE7L","schema_version":"1.0","canonical_sha256":"1dae0a93eb9cb80a1378d605d5679a4ecbbea4eebacd5c7bf8f166d0019b9ef6","source":{"kind":"arxiv","id":"2106.09009","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Spoken Language Understanding for Generalized Voice Assistants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Athanasios Mouchtaris, Joseph P. McKenna, Michael Saxon, Samridhi Choudhary","submitted_at":"2021-06-16T17:56:47Z","abstract_excerpt":"End-to-end (E2E) spoken language understanding (SLU) systems predict utterance semantics directly from speech using a single model. Previous work in this area has focused on targeted tasks in fixed domains, where the output semantic structure is assumed a priori and the input speech is of limited complexity. In this work we present our approach to developing an E2E model for generalized SLU in commercial voice assistants (VAs). We propose a fully differentiable, transformer-based, hierarchical system that can be pretrained at both the ASR and NLU levels. This is then fine-tuned on both transcr"},"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":"2106.09009","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-16T17:56:47Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"3dad91a84d0f81b8e870bd83899666e96eb62f63237450ea3471e78e264f7902","abstract_canon_sha256":"394a9b1b765eb87cdd652f863f152fd6e54eb41c334b77451733f3985bf5afde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:36.664133Z","signature_b64":"zMCkWjt3Bwp6bSnz27aSQl//2DvEwehdy5JHWXFf8P+gRY4neTo5umm1zrdPPMUBQkTLUpkS03cvnMFeOpiqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dae0a93eb9cb80a1378d605d5679a4ecbbea4eebacd5c7bf8f166d0019b9ef6","last_reissued_at":"2026-07-05T03:20:36.663635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:36.663635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Spoken Language Understanding for Generalized Voice Assistants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Athanasios Mouchtaris, Joseph P. McKenna, Michael Saxon, Samridhi Choudhary","submitted_at":"2021-06-16T17:56:47Z","abstract_excerpt":"End-to-end (E2E) spoken language understanding (SLU) systems predict utterance semantics directly from speech using a single model. Previous work in this area has focused on targeted tasks in fixed domains, where the output semantic structure is assumed a priori and the input speech is of limited complexity. In this work we present our approach to developing an E2E model for generalized SLU in commercial voice assistants (VAs). We propose a fully differentiable, transformer-based, hierarchical system that can be pretrained at both the ASR and NLU levels. This is then fine-tuned on both transcr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09009","kind":"arxiv","version":2},"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/2106.09009/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":"2106.09009","created_at":"2026-07-05T03:20:36.663701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09009v2","created_at":"2026-07-05T03:20:36.663701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09009","created_at":"2026-07-05T03:20:36.663701+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWXAVE7LTS4A","created_at":"2026-07-05T03:20:36.663701+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWXAVE7LTS4AUE3Y","created_at":"2026-07-05T03:20:36.663701+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWXAVE7L","created_at":"2026-07-05T03:20:36.663701+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/DWXAVE7LTS4AUE3Y2YC5KZ42J3","json":"https://pith.science/pith/DWXAVE7LTS4AUE3Y2YC5KZ42J3.json","graph_json":"https://pith.science/api/pith-number/DWXAVE7LTS4AUE3Y2YC5KZ42J3/graph.json","events_json":"https://pith.science/api/pith-number/DWXAVE7LTS4AUE3Y2YC5KZ42J3/events.json","paper":"https://pith.science/paper/DWXAVE7L"},"agent_actions":{"view_html":"https://pith.science/pith/DWXAVE7LTS4AUE3Y2YC5KZ42J3","download_json":"https://pith.science/pith/DWXAVE7LTS4AUE3Y2YC5KZ42J3.json","view_paper":"https://pith.science/paper/DWXAVE7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09009&json=true","fetch_graph":"https://pith.science/api/pith-number/DWXAVE7LTS4AUE3Y2YC5KZ42J3/graph.json","fetch_events":"https://pith.science/api/pith-number/DWXAVE7LTS4AUE3Y2YC5KZ42J3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWXAVE7LTS4AUE3Y2YC5KZ42J3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWXAVE7LTS4AUE3Y2YC5KZ42J3/action/storage_attestation","attest_author":"https://pith.science/pith/DWXAVE7LTS4AUE3Y2YC5KZ42J3/action/author_attestation","sign_citation":"https://pith.science/pith/DWXAVE7LTS4AUE3Y2YC5KZ42J3/action/citation_signature","submit_replication":"https://pith.science/pith/DWXAVE7LTS4AUE3Y2YC5KZ42J3/action/replication_record"}},"created_at":"2026-07-05T03:20:36.663701+00:00","updated_at":"2026-07-05T03:20:36.663701+00:00"}