{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GE2X2X4P5TMMXEVGRDBEWPXH4F","short_pith_number":"pith:GE2X2X4P","schema_version":"1.0","canonical_sha256":"31357d5f8fecd8cb92a688c24b3ee7e16e4cbef12f88ed671b06df0f330f0636","source":{"kind":"arxiv","id":"2411.00023","version":2},"attestation_state":"computed","paper":{"title":"Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahmed H. Abdelaziz, Ahmed Tewfik, Ognjen (Oggi) Rudovic, Pranay Dighe, Sameer Dharur, Saurabh Adya, Vineet Garg, Xiaochuan Niu, Yi Su","submitted_at":"2024-10-28T19:43:43Z","abstract_excerpt":"Follow-up conversations with virtual assistants (VAs) enable a user to seamlessly interact with a VA without the need to repeatedly invoke it using a keyword (after the first query). Therefore, accurate Device-directed Speech Detection (DDSD) from the follow-up queries is critical for enabling naturalistic user experience. To this end, we explore the notion of Large Language Models (LLMs) and model the first query when making inference about the follow-ups (based on the ASR-decoded text), via prompting of a pretrained LLM, or by adapting a binary classifier on top of the LLM. In doing so, we a"},"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":"2411.00023","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-28T19:43:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"cb6283e9b8ac628d2dd70a6a95c5a61fc832f51fe33c3bcae513d7f9e8177b6a","abstract_canon_sha256":"4341bb0bcf4f589ffcb39548b7b6de40089f754886988135725939ff6a20d033"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:10.515956Z","signature_b64":"/je3IGmH0EcOumxE0vLXaZQn6de9pXQliVRJ39CFMA+cnEV7jJODSSY1TOgn8eu8ydb01wn/tzAEp6z0bUmZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31357d5f8fecd8cb92a688c24b3ee7e16e4cbef12f88ed671b06df0f330f0636","last_reissued_at":"2026-07-05T09:31:10.515468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:10.515468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahmed H. Abdelaziz, Ahmed Tewfik, Ognjen (Oggi) Rudovic, Pranay Dighe, Sameer Dharur, Saurabh Adya, Vineet Garg, Xiaochuan Niu, Yi Su","submitted_at":"2024-10-28T19:43:43Z","abstract_excerpt":"Follow-up conversations with virtual assistants (VAs) enable a user to seamlessly interact with a VA without the need to repeatedly invoke it using a keyword (after the first query). Therefore, accurate Device-directed Speech Detection (DDSD) from the follow-up queries is critical for enabling naturalistic user experience. To this end, we explore the notion of Large Language Models (LLMs) and model the first query when making inference about the follow-ups (based on the ASR-decoded text), via prompting of a pretrained LLM, or by adapting a binary classifier on top of the LLM. In doing so, we a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00023","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/2411.00023/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":"2411.00023","created_at":"2026-07-05T09:31:10.515543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00023v2","created_at":"2026-07-05T09:31:10.515543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00023","created_at":"2026-07-05T09:31:10.515543+00:00"},{"alias_kind":"pith_short_12","alias_value":"GE2X2X4P5TMM","created_at":"2026-07-05T09:31:10.515543+00:00"},{"alias_kind":"pith_short_16","alias_value":"GE2X2X4P5TMMXEVG","created_at":"2026-07-05T09:31:10.515543+00:00"},{"alias_kind":"pith_short_8","alias_value":"GE2X2X4P","created_at":"2026-07-05T09:31:10.515543+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/GE2X2X4P5TMMXEVGRDBEWPXH4F","json":"https://pith.science/pith/GE2X2X4P5TMMXEVGRDBEWPXH4F.json","graph_json":"https://pith.science/api/pith-number/GE2X2X4P5TMMXEVGRDBEWPXH4F/graph.json","events_json":"https://pith.science/api/pith-number/GE2X2X4P5TMMXEVGRDBEWPXH4F/events.json","paper":"https://pith.science/paper/GE2X2X4P"},"agent_actions":{"view_html":"https://pith.science/pith/GE2X2X4P5TMMXEVGRDBEWPXH4F","download_json":"https://pith.science/pith/GE2X2X4P5TMMXEVGRDBEWPXH4F.json","view_paper":"https://pith.science/paper/GE2X2X4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00023&json=true","fetch_graph":"https://pith.science/api/pith-number/GE2X2X4P5TMMXEVGRDBEWPXH4F/graph.json","fetch_events":"https://pith.science/api/pith-number/GE2X2X4P5TMMXEVGRDBEWPXH4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GE2X2X4P5TMMXEVGRDBEWPXH4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GE2X2X4P5TMMXEVGRDBEWPXH4F/action/storage_attestation","attest_author":"https://pith.science/pith/GE2X2X4P5TMMXEVGRDBEWPXH4F/action/author_attestation","sign_citation":"https://pith.science/pith/GE2X2X4P5TMMXEVGRDBEWPXH4F/action/citation_signature","submit_replication":"https://pith.science/pith/GE2X2X4P5TMMXEVGRDBEWPXH4F/action/replication_record"}},"created_at":"2026-07-05T09:31:10.515543+00:00","updated_at":"2026-07-05T09:31:10.515543+00:00"}