{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LKJ32RHJ5SSCY5SW25XMQ56BLW","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":"98caf53d4d90dc5337c0c55c160d50182fa2279335d84c808dd2686173239d08","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-23T15:35:03Z","title_canon_sha256":"e3d766ff2207acb0778c0fb86aae2ce0c432810ae134c913cb8ddff98ac003ec"},"schema_version":"1.0","source":{"id":"2010.12484","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12484","created_at":"2026-07-05T02:31:20Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12484v3","created_at":"2026-07-05T02:31:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12484","created_at":"2026-07-05T02:31:20Z"},{"alias_kind":"pith_short_12","alias_value":"LKJ32RHJ5SSC","created_at":"2026-07-05T02:31:20Z"},{"alias_kind":"pith_short_16","alias_value":"LKJ32RHJ5SSCY5SW","created_at":"2026-07-05T02:31:20Z"},{"alias_kind":"pith_short_8","alias_value":"LKJ32RHJ","created_at":"2026-07-05T02:31:20Z"}],"graph_snapshots":[{"event_id":"sha256:89b37264e1ccd56f2dcebffed33b691fdf0402a5bbd4e2262144c3c34427d513","target":"graph","created_at":"2026-07-05T02:31:20Z","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/2010.12484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust voice activity detection (VAD) is a challenging task in low signal-to-noise (SNR) environments. Recent studies show that speech enhancement is helpful to VAD, but the performance improvement is limited. To address this issue, here we propose a speech enhancement aided end-to-end multi-task model for VAD. The model has two decoders, one for speech enhancement and the other for VAD. The two decoders share the same encoder and speech separation network. Unlike the direct thought that takes two separated objectives for VAD and speech enhancement respectively, here we propose a new joint opt","authors_text":"Xiao-Lei Zhang, Xu Tan","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-23T15:35:03Z","title":"Speech enhancement aided end-to-end multi-task learning for voice activity detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12484","kind":"arxiv","version":3},"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":"sha256:50cbeaf6735e9112e307914987957ee3d50993da60646719b8ef2e4c1fcd7cca","target":"record","created_at":"2026-07-05T02:31:20Z","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":"98caf53d4d90dc5337c0c55c160d50182fa2279335d84c808dd2686173239d08","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-23T15:35:03Z","title_canon_sha256":"e3d766ff2207acb0778c0fb86aae2ce0c432810ae134c913cb8ddff98ac003ec"},"schema_version":"1.0","source":{"id":"2010.12484","kind":"arxiv","version":3}},"canonical_sha256":"5a93bd44e9eca42c7656d76ec877c15dbe4d93feb6938f50454e1111459f24b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a93bd44e9eca42c7656d76ec877c15dbe4d93feb6938f50454e1111459f24b1","first_computed_at":"2026-07-05T02:31:20.272740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:20.272740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VxjCG/fSYIUu6j9cLmmoW8KY+PNpZs3/pzXQPY+2nluP7tDwAV4ZQjvZcBLWAaJFec3AwrB/HbOAp71cIfaIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:20.273228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12484","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50cbeaf6735e9112e307914987957ee3d50993da60646719b8ef2e4c1fcd7cca","sha256:89b37264e1ccd56f2dcebffed33b691fdf0402a5bbd4e2262144c3c34427d513"],"state_sha256":"c581c68b0bb3caad04cc50c0637888f5146f9875359c4ab3f0531cb1a4a90239"}