{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SQMQ7ZLUEJLOEC5KNMO4NDKKUZ","short_pith_number":"pith:SQMQ7ZLU","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"},"canonical_sha256":"94190fe5742256e20baa6b1dc68d4aa67bb302e4b2ff2c07801da5db55a7a982","source":{"kind":"arxiv","id":"2305.12450","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12450","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12450v1","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12450","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"SQMQ7ZLUEJLO","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"SQMQ7ZLUEJLOEC5K","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"SQMQ7ZLU","created_at":"2026-07-05T06:12:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SQMQ7ZLUEJLOEC5KNMO4NDKKUZ","target":"record","payload":{"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"},"canonical_sha256":"94190fe5742256e20baa6b1dc68d4aa67bb302e4b2ff2c07801da5db55a7a982","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"},"source_kind":"arxiv","source_id":"2305.12450","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:12:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fteQhIMWCH59kTXsyrzbrJ0aezi+esXysR0caWWCtclKusx98F6p3+TAvVl5AckAIUYvnJZmEHQA2f4RHYT+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:54:34.728651Z"},"content_sha256":"e5ee1a26ce1a287d82d89f351ae24d9edca08a127380078616ccc0b9f3b58a57","schema_version":"1.0","event_id":"sha256:e5ee1a26ce1a287d82d89f351ae24d9edca08a127380078616ccc0b9f3b58a57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SQMQ7ZLUEJLOEC5KNMO4NDKKUZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:12:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1b/L+a8MQCqgPmkREa1WlBa2HZGaC5ezouFevNMme/Kj7gxwd7Nk3+OtwrGTDNAKU5yhZL6UUMsb7iXlaxrGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:54:34.729029Z"},"content_sha256":"9fdb81052ec98bb5aa580736e5c0946c8fb713f8d8e9c6113d57d893e43d9d2a","schema_version":"1.0","event_id":"sha256:9fdb81052ec98bb5aa580736e5c0946c8fb713f8d8e9c6113d57d893e43d9d2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/bundle.json","state_url":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T09:54:34Z","links":{"resolver":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ","bundle":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/bundle.json","state":"https://pith.science/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQMQ7ZLUEJLOEC5KNMO4NDKKUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SQMQ7ZLUEJLOEC5KNMO4NDKKUZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fce517da74a36c4e83ab54d2b5ec5d4befde82c538805b3f6e079f3bdf80815b","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-21T13:02:53Z","title_canon_sha256":"460b3051a469b0a6f29e228f2c8387164344af84573b65b592a808a09bae2fc6"},"schema_version":"1.0","source":{"id":"2305.12450","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12450","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12450v1","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12450","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"SQMQ7ZLUEJLO","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"SQMQ7ZLUEJLOEC5K","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"SQMQ7ZLU","created_at":"2026-07-05T06:12:10Z"}],"graph_snapshots":[{"event_id":"sha256:9fdb81052ec98bb5aa580736e5c0946c8fb713f8d8e9c6113d57d893e43d9d2a","target":"graph","created_at":"2026-07-05T06:12:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.12450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jie Zhang, Lingyun Zuo, Li-Rong Dai, Mohan Shi, Qian Chen, Shiliang Zhang, Yuchun Shu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-21T13:02:53Z","title":"Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12450","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e5ee1a26ce1a287d82d89f351ae24d9edca08a127380078616ccc0b9f3b58a57","target":"record","created_at":"2026-07-05T06:12:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fce517da74a36c4e83ab54d2b5ec5d4befde82c538805b3f6e079f3bdf80815b","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-21T13:02:53Z","title_canon_sha256":"460b3051a469b0a6f29e228f2c8387164344af84573b65b592a808a09bae2fc6"},"schema_version":"1.0","source":{"id":"2305.12450","kind":"arxiv","version":1}},"canonical_sha256":"94190fe5742256e20baa6b1dc68d4aa67bb302e4b2ff2c07801da5db55a7a982","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94190fe5742256e20baa6b1dc68d4aa67bb302e4b2ff2c07801da5db55a7a982","first_computed_at":"2026-07-05T06:12:10.756387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:10.756387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6kE2ZpWzEelzEeGt/8SZ+A/dKxCCkL2HXE8vLK17ZViPi0wMNZ3/QIR1waHmdzROLhlyTM0lN6E4o1ZBB6noBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:10.756845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12450","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5ee1a26ce1a287d82d89f351ae24d9edca08a127380078616ccc0b9f3b58a57","sha256:9fdb81052ec98bb5aa580736e5c0946c8fb713f8d8e9c6113d57d893e43d9d2a"],"state_sha256":"8725e542ac99a2c575a794d9052d30ec16d023cdee433b2a992a51d196802469"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yvh5EGN1oGgzl225zlrVbhScjfxxbXxTxiHhvXAWYeCzl/OtjE0XLzIFK4Zo5zBpql+yttcyZDcuT1SjaJXyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:54:34.731017Z","bundle_sha256":"b87a80787d1c314cbff9a41246a8e5bba35e2411d3f38bef2f11cf08ee564cfa"}}