{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L4XVFA5UDWAP5G4JVG4S677BW6","short_pith_number":"pith:L4XVFA5U","schema_version":"1.0","canonical_sha256":"5f2f5283b41d80fe9b89a9b92f7fe1b7afa91348b11f48403306c7bc0b6f5533","source":{"kind":"arxiv","id":"2506.07081","version":2},"attestation_state":"computed","paper":{"title":"Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jan Cernocky, Petr Schwarz, Sathvik Udupa, Shinji Watanabe","submitted_at":"2025-06-08T10:54:23Z","abstract_excerpt":"Accurate, low-latency endpointing is crucial for effective spoken dialogue systems. While traditional endpointers often rely on spectrum-based audio features, this work proposes real-time speech endpointing for multi-turn dialogues using streaming, low-bitrate Neural Audio Codec (NAC) features, building upon recent advancements in neural audio codecs. To further reduce cutoff errors, we introduce a novel label delay training scheme. At a fixed median latency of 160 ms, our combined NAC and label delay approach achieves significant relative cutoff error reductions: 42.7% for a single-stream end"},"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":"2506.07081","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-08T10:54:23Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d76865f605ca589bf74f590d0952ddc9ae0524486155948fbd9ea70936ce40e6","abstract_canon_sha256":"c3290f23804a91109934df6a55f6fb8a164e0343b194faf3e43a1eda1347f86b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:22.343203Z","signature_b64":"0W3ObtLK1Qx/iT4Y8g8ZfW2cD0tfprTSPBQ6JLsg+DRxAqKIxGzaGAZfhTnMwRbCjSdkfB2+HUtd69a29nxEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f2f5283b41d80fe9b89a9b92f7fe1b7afa91348b11f48403306c7bc0b6f5533","last_reissued_at":"2026-07-05T11:24:22.342640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:22.342640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jan Cernocky, Petr Schwarz, Sathvik Udupa, Shinji Watanabe","submitted_at":"2025-06-08T10:54:23Z","abstract_excerpt":"Accurate, low-latency endpointing is crucial for effective spoken dialogue systems. While traditional endpointers often rely on spectrum-based audio features, this work proposes real-time speech endpointing for multi-turn dialogues using streaming, low-bitrate Neural Audio Codec (NAC) features, building upon recent advancements in neural audio codecs. To further reduce cutoff errors, we introduce a novel label delay training scheme. At a fixed median latency of 160 ms, our combined NAC and label delay approach achieves significant relative cutoff error reductions: 42.7% for a single-stream end"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07081","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/2506.07081/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":"2506.07081","created_at":"2026-07-05T11:24:22.342717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07081v2","created_at":"2026-07-05T11:24:22.342717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07081","created_at":"2026-07-05T11:24:22.342717+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4XVFA5UDWAP","created_at":"2026-07-05T11:24:22.342717+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4XVFA5UDWAP5G4J","created_at":"2026-07-05T11:24:22.342717+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4XVFA5U","created_at":"2026-07-05T11:24:22.342717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13450","citing_title":"Endpoint Anticipation for Low-Latency Spoken Dialogue","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4XVFA5UDWAP5G4JVG4S677BW6","json":"https://pith.science/pith/L4XVFA5UDWAP5G4JVG4S677BW6.json","graph_json":"https://pith.science/api/pith-number/L4XVFA5UDWAP5G4JVG4S677BW6/graph.json","events_json":"https://pith.science/api/pith-number/L4XVFA5UDWAP5G4JVG4S677BW6/events.json","paper":"https://pith.science/paper/L4XVFA5U"},"agent_actions":{"view_html":"https://pith.science/pith/L4XVFA5UDWAP5G4JVG4S677BW6","download_json":"https://pith.science/pith/L4XVFA5UDWAP5G4JVG4S677BW6.json","view_paper":"https://pith.science/paper/L4XVFA5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07081&json=true","fetch_graph":"https://pith.science/api/pith-number/L4XVFA5UDWAP5G4JVG4S677BW6/graph.json","fetch_events":"https://pith.science/api/pith-number/L4XVFA5UDWAP5G4JVG4S677BW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4XVFA5UDWAP5G4JVG4S677BW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4XVFA5UDWAP5G4JVG4S677BW6/action/storage_attestation","attest_author":"https://pith.science/pith/L4XVFA5UDWAP5G4JVG4S677BW6/action/author_attestation","sign_citation":"https://pith.science/pith/L4XVFA5UDWAP5G4JVG4S677BW6/action/citation_signature","submit_replication":"https://pith.science/pith/L4XVFA5UDWAP5G4JVG4S677BW6/action/replication_record"}},"created_at":"2026-07-05T11:24:22.342717+00:00","updated_at":"2026-07-05T11:24:22.342717+00:00"}