{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJFE4ATMOSLLAHBDD4MWQ56A42","short_pith_number":"pith:JJFE4ATM","schema_version":"1.0","canonical_sha256":"4a4a4e026c7496b01c231f196877c0e6bbacb8891e02fd08b976e75d0bac8dfb","source":{"kind":"arxiv","id":"2606.18094","version":1},"attestation_state":"computed","paper":{"title":"Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Huu Quyen Dang, Jiajun Deng, Nikita Kuzmin, Simon Lui, Tao Zhong, Tianxiang Cao, Tristan Tsoi, Yingke Zhu","submitted_at":"2026-06-16T15:58:36Z","abstract_excerpt":"Endpoint detection (EPD) is essential for natural turn-taking in streaming speech systems. However, reliably determining the endpoint of an utterance is challenging because speakers often pause mid-utterance due to hesitations and disfluencies. Semantic EPD has emerged as a promising direction to address this issue but is hindered by ambiguous supervision and strict streaming constraints. We propose Next-Turn that uses the time-to-next-speech-onset as the training objective, where targets are derived directly from speech timestamps and require no additional annotation. Experiments show that th"},"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":"2606.18094","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-16T15:58:36Z","cross_cats_sorted":[],"title_canon_sha256":"189f16d39fe503d0e09157e98647f4a8f737968ee7f3160127fef5a0a32ed1cd","abstract_canon_sha256":"ecdf5bc6c298e2873712ec954ffc784ba996f175c465c6f234608899707b8315"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:48.384993Z","signature_b64":"LBQf2aWRuki0+pRwbZPXbon7+v+MW9jxKDv1UtkpV2/FpJ8lLsPvrsLmI+AlKasTIEGZVd81g8pEALlocj4DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a4a4e026c7496b01c231f196877c0e6bbacb8891e02fd08b976e75d0bac8dfb","last_reissued_at":"2026-06-19T16:10:48.384579Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:48.384579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Huu Quyen Dang, Jiajun Deng, Nikita Kuzmin, Simon Lui, Tao Zhong, Tianxiang Cao, Tristan Tsoi, Yingke Zhu","submitted_at":"2026-06-16T15:58:36Z","abstract_excerpt":"Endpoint detection (EPD) is essential for natural turn-taking in streaming speech systems. However, reliably determining the endpoint of an utterance is challenging because speakers often pause mid-utterance due to hesitations and disfluencies. Semantic EPD has emerged as a promising direction to address this issue but is hindered by ambiguous supervision and strict streaming constraints. We propose Next-Turn that uses the time-to-next-speech-onset as the training objective, where targets are derived directly from speech timestamps and require no additional annotation. Experiments show that th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18094","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/2606.18094/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":"2606.18094","created_at":"2026-06-19T16:10:48.384644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18094v1","created_at":"2026-06-19T16:10:48.384644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18094","created_at":"2026-06-19T16:10:48.384644+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJFE4ATMOSLL","created_at":"2026-06-19T16:10:48.384644+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJFE4ATMOSLLAHBD","created_at":"2026-06-19T16:10:48.384644+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJFE4ATM","created_at":"2026-06-19T16:10:48.384644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.18094","citing_title":"Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJFE4ATMOSLLAHBDD4MWQ56A42","json":"https://pith.science/pith/JJFE4ATMOSLLAHBDD4MWQ56A42.json","graph_json":"https://pith.science/api/pith-number/JJFE4ATMOSLLAHBDD4MWQ56A42/graph.json","events_json":"https://pith.science/api/pith-number/JJFE4ATMOSLLAHBDD4MWQ56A42/events.json","paper":"https://pith.science/paper/JJFE4ATM"},"agent_actions":{"view_html":"https://pith.science/pith/JJFE4ATMOSLLAHBDD4MWQ56A42","download_json":"https://pith.science/pith/JJFE4ATMOSLLAHBDD4MWQ56A42.json","view_paper":"https://pith.science/paper/JJFE4ATM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18094&json=true","fetch_graph":"https://pith.science/api/pith-number/JJFE4ATMOSLLAHBDD4MWQ56A42/graph.json","fetch_events":"https://pith.science/api/pith-number/JJFE4ATMOSLLAHBDD4MWQ56A42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJFE4ATMOSLLAHBDD4MWQ56A42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJFE4ATMOSLLAHBDD4MWQ56A42/action/storage_attestation","attest_author":"https://pith.science/pith/JJFE4ATMOSLLAHBDD4MWQ56A42/action/author_attestation","sign_citation":"https://pith.science/pith/JJFE4ATMOSLLAHBDD4MWQ56A42/action/citation_signature","submit_replication":"https://pith.science/pith/JJFE4ATMOSLLAHBDD4MWQ56A42/action/replication_record"}},"created_at":"2026-06-19T16:10:48.384644+00:00","updated_at":"2026-06-19T16:10:48.384644+00:00"}