{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SQMQ7ZLUEJLOEC5KNMO4NDKKUZ","short_pith_number":"pith:SQMQ7ZLU","schema_version":"1.0","canonical_sha256":"94190fe5742256e20baa6b1dc68d4aa67bb302e4b2ff2c07801da5db55a7a982","source":{"kind":"arxiv","id":"2305.12450","version":1},"attestation_state":"computed","paper":{"title":"Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jie Zhang, Lingyun Zuo, Li-Rong Dai, Mohan Shi, Qian Chen, Shiliang Zhang, Yuchun Shu","submitted_at":"2023-05-21T13:02:53Z","abstract_excerpt":"For speech interaction, voice activity detection (VAD) is often used as a front-end. However, traditional VAD algorithms usually need to wait for a continuous tail silence to reach a preset maximum duration before segmentation, resulting in a large latency that affects user experience. In this paper, we propose a novel semantic VAD for low-latency segmentation. Different from existing methods, a frame-level punctuation prediction task is added to the semantic VAD, and the artificial endpoint is included in the classification category in addition to the often-used speech presence and absence. T"},"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":"2305.12450","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-21T13:02:53Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"460b3051a469b0a6f29e228f2c8387164344af84573b65b592a808a09bae2fc6","abstract_canon_sha256":"fce517da74a36c4e83ab54d2b5ec5d4befde82c538805b3f6e079f3bdf80815b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:10.756845Z","signature_b64":"6kE2ZpWzEelzEeGt/8SZ+A/dKxCCkL2HXE8vLK17ZViPi0wMNZ3/QIR1waHmdzROLhlyTM0lN6E4o1ZBB6noBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94190fe5742256e20baa6b1dc68d4aa67bb302e4b2ff2c07801da5db55a7a982","last_reissued_at":"2026-07-05T06:12:10.756387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:10.756387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jie Zhang, Lingyun Zuo, Li-Rong Dai, Mohan Shi, Qian Chen, Shiliang Zhang, Yuchun Shu","submitted_at":"2023-05-21T13:02:53Z","abstract_excerpt":"For speech interaction, voice activity detection (VAD) is often used as a front-end. However, traditional VAD algorithms usually need to wait for a continuous tail silence to reach a preset maximum duration before segmentation, resulting in a large latency that affects user experience. In this paper, we propose a novel semantic VAD for low-latency segmentation. Different from existing methods, a frame-level punctuation prediction task is added to the semantic VAD, and the artificial endpoint is included in the classification category in addition to the often-used speech presence and absence. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12450","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/2305.12450/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":"2305.12450","created_at":"2026-07-05T06:12:10.756445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12450v1","created_at":"2026-07-05T06:12:10.756445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12450","created_at":"2026-07-05T06:12:10.756445+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQMQ7ZLUEJLO","created_at":"2026-07-05T06:12:10.756445+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQMQ7ZLUEJLOEC5K","created_at":"2026-07-05T06:12:10.756445+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQMQ7ZLU","created_at":"2026-07-05T06:12:10.756445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18094","citing_title":"Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ","json":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ.json","graph_json":"https://pith.science/api/pith-number/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/graph.json","events_json":"https://pith.science/api/pith-number/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/events.json","paper":"https://pith.science/paper/SQMQ7ZLU"},"agent_actions":{"view_html":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ","download_json":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ.json","view_paper":"https://pith.science/paper/SQMQ7ZLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12450&json=true","fetch_graph":"https://pith.science/api/pith-number/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/action/storage_attestation","attest_author":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/action/author_attestation","sign_citation":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/action/citation_signature","submit_replication":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/action/replication_record"}},"created_at":"2026-07-05T06:12:10.756445+00:00","updated_at":"2026-07-05T06:12:10.756445+00:00"}