{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SWPRCCDPN6QWS3NK2CMPGL23QH","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":"2bda839df58eb8b13bf9015b30beeb8b27ee437c6f4db0ef31b5f7fb7e2bbc4f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-08-12T17:54:31Z","title_canon_sha256":"ff17631778ffce3d3620bea538dc11032336458bacc47c55a95a6fdd2766430b"},"schema_version":"1.0","source":{"id":"1908.04284","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04284","created_at":"2026-07-05T00:53:51Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04284v4","created_at":"2026-07-05T00:53:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04284","created_at":"2026-07-05T00:53:51Z"},{"alias_kind":"pith_short_12","alias_value":"SWPRCCDPN6QW","created_at":"2026-07-05T00:53:51Z"},{"alias_kind":"pith_short_16","alias_value":"SWPRCCDPN6QWS3NK","created_at":"2026-07-05T00:53:51Z"},{"alias_kind":"pith_short_8","alias_value":"SWPRCCDP","created_at":"2026-07-05T00:53:51Z"}],"graph_snapshots":[{"event_id":"sha256:e6c24040ead2d0f68ae89837ce1bd4632b2afe0672d3089d385e0bbfd1e322d5","target":"graph","created_at":"2026-07-05T00:53:51Z","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/1908.04284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose \"personal VAD\", a system to detect the voice activity of a target speaker at the frame level. This system is useful for gating the inputs to a streaming on-device speech recognition system, such that it only triggers for the target user, which helps reduce the computational cost and battery consumption, especially in scenarios where a keyword detector is unpreferable. We achieve this by training a VAD-alike neural network that is conditioned on the target speaker embedding or the speaker verification score. For each frame, personal VAD outputs the probabilities for th","authors_text":"Ignacio Lopez Moreno, Li Wan, Quan Wang, Shaojin Ding, Shuo-yiin Chang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-08-12T17:54:31Z","title":"Personal VAD: Speaker-Conditioned Voice Activity Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04284","kind":"arxiv","version":4},"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":"sha256:912807021a6082bd2a5b6caf05c3280e4e9d7dcbeec1afabecd4a6314a107e24","target":"record","created_at":"2026-07-05T00:53:51Z","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":"2bda839df58eb8b13bf9015b30beeb8b27ee437c6f4db0ef31b5f7fb7e2bbc4f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-08-12T17:54:31Z","title_canon_sha256":"ff17631778ffce3d3620bea538dc11032336458bacc47c55a95a6fdd2766430b"},"schema_version":"1.0","source":{"id":"1908.04284","kind":"arxiv","version":4}},"canonical_sha256":"959f11086f6fa1696daad098f32f5b81dfa67e839a7b9ee10ac5558e8c1d9f02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"959f11086f6fa1696daad098f32f5b81dfa67e839a7b9ee10ac5558e8c1d9f02","first_computed_at":"2026-07-05T00:53:51.090846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:53:51.090846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7yWsLvF3elk71Piq5SWKiSsljpbgRHyn03i6PCmBe3FllY904iY17hWUm1/Q5gJ21MLH4XzfHwOnlP/UNumsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:53:51.091272Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04284","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:912807021a6082bd2a5b6caf05c3280e4e9d7dcbeec1afabecd4a6314a107e24","sha256:e6c24040ead2d0f68ae89837ce1bd4632b2afe0672d3089d385e0bbfd1e322d5"],"state_sha256":"9696143bc83083e4264a1e2922b2ced2c00efddf73cb09558b00ae3395d516bb"}