{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2YHQE47CLUBBHODFIIZRW5SMDG","short_pith_number":"pith:2YHQE47C","canonical_record":{"source":{"id":"2203.02944","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-06T11:52:00Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"51135051aac5551cdf946252d21922c55b76d504f4e9d32ab72805e4572e2e4b","abstract_canon_sha256":"6d68cfb5afcb8e6df58e78b97e3a77ff7ade38e91f30128b236b101f336e6fe4"},"schema_version":"1.0"},"canonical_sha256":"d60f0273e25d0213b86542331b764c198ec874def6ea5470022330ccf83b8be3","source":{"kind":"arxiv","id":"2203.02944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02944","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02944v1","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02944","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"2YHQE47CLUBB","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"2YHQE47CLUBBHODF","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"2YHQE47C","created_at":"2026-07-05T04:02:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2YHQE47CLUBBHODFIIZRW5SMDG","target":"record","payload":{"canonical_record":{"source":{"id":"2203.02944","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-06T11:52:00Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"51135051aac5551cdf946252d21922c55b76d504f4e9d32ab72805e4572e2e4b","abstract_canon_sha256":"6d68cfb5afcb8e6df58e78b97e3a77ff7ade38e91f30128b236b101f336e6fe4"},"schema_version":"1.0"},"canonical_sha256":"d60f0273e25d0213b86542331b764c198ec874def6ea5470022330ccf83b8be3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:29.288487Z","signature_b64":"7JBk3JluNAQSkgvk4AZkPJTpdRsYiOkerY93/kbRaPg8mjR95Pq30KImZ7hlTavEe3weRLKgUxGVO8ZzhYDdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d60f0273e25d0213b86542331b764c198ec874def6ea5470022330ccf83b8be3","last_reissued_at":"2026-07-05T04:02:29.288089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:29.288089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.02944","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":"2026-07-05T04:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lrRsAEbvvoRsawF2U6T0ntJ2/tNvwYIl1TnYUUj7bBOMaJVyl0575G28s6GQNj+erFdh4jc1TfNL+/zHbVTMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:23:17.575476Z"},"content_sha256":"a64d6cde542476844c3d236cafedaad6f334ba4a6ff09391faf3d428b873ee84","schema_version":"1.0","event_id":"sha256:a64d6cde542476844c3d236cafedaad6f334ba4a6ff09391faf3d428b873ee84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2YHQE47CLUBBHODFIIZRW5SMDG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CNN self-attention voice activity detector","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Amit Sofer, Shlomo E. Chazan","submitted_at":"2022-03-06T11:52:00Z","abstract_excerpt":"In this work we present a novel single-channel Voice Activity Detector (VAD) approach. We utilize a Convolutional Neural Network (CNN) which exploits the spatial information of the noisy input spectrum to extract frame-wise embedding sequence, followed by a Self Attention (SA) Encoder with a goal of finding contextual information from the embedding sequence. Different from previous works which were employed on each frame (with context frames) separately, our method is capable of processing the entire signal at once, and thus enabling long receptive field. We show that the fusion of CNN and SA "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02944","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/2203.02944/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":"2026-07-05T04:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z/69zCB5nSzBIDVQrH7kLg2lmL6w/XD41WLNBK5VlDD0FJAwB9CmEGUDv+sqcWKpeW2W3RpIVEFCKMdZ2N6CDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:23:17.575978Z"},"content_sha256":"fb9d1279161104d67931a1fce559bd68b1b71635c3d1a732d7e335c22f9d0072","schema_version":"1.0","event_id":"sha256:fb9d1279161104d67931a1fce559bd68b1b71635c3d1a732d7e335c22f9d0072"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YHQE47CLUBBHODFIIZRW5SMDG/bundle.json","state_url":"https://pith.science/pith/2YHQE47CLUBBHODFIIZRW5SMDG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YHQE47CLUBBHODFIIZRW5SMDG/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":"2026-08-06T05:23:17Z","links":{"resolver":"https://pith.science/pith/2YHQE47CLUBBHODFIIZRW5SMDG","bundle":"https://pith.science/pith/2YHQE47CLUBBHODFIIZRW5SMDG/bundle.json","state":"https://pith.science/pith/2YHQE47CLUBBHODFIIZRW5SMDG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YHQE47CLUBBHODFIIZRW5SMDG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2YHQE47CLUBBHODFIIZRW5SMDG","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":"6d68cfb5afcb8e6df58e78b97e3a77ff7ade38e91f30128b236b101f336e6fe4","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-06T11:52:00Z","title_canon_sha256":"51135051aac5551cdf946252d21922c55b76d504f4e9d32ab72805e4572e2e4b"},"schema_version":"1.0","source":{"id":"2203.02944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02944","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02944v1","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02944","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"2YHQE47CLUBB","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"2YHQE47CLUBBHODF","created_at":"2026-07-05T04:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"2YHQE47C","created_at":"2026-07-05T04:02:29Z"}],"graph_snapshots":[{"event_id":"sha256:fb9d1279161104d67931a1fce559bd68b1b71635c3d1a732d7e335c22f9d0072","target":"graph","created_at":"2026-07-05T04:02:29Z","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/2203.02944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work we present a novel single-channel Voice Activity Detector (VAD) approach. We utilize a Convolutional Neural Network (CNN) which exploits the spatial information of the noisy input spectrum to extract frame-wise embedding sequence, followed by a Self Attention (SA) Encoder with a goal of finding contextual information from the embedding sequence. Different from previous works which were employed on each frame (with context frames) separately, our method is capable of processing the entire signal at once, and thus enabling long receptive field. We show that the fusion of CNN and SA ","authors_text":"Amit Sofer, Shlomo E. Chazan","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-06T11:52:00Z","title":"CNN self-attention voice activity detector"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02944","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:a64d6cde542476844c3d236cafedaad6f334ba4a6ff09391faf3d428b873ee84","target":"record","created_at":"2026-07-05T04:02:29Z","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":"6d68cfb5afcb8e6df58e78b97e3a77ff7ade38e91f30128b236b101f336e6fe4","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-06T11:52:00Z","title_canon_sha256":"51135051aac5551cdf946252d21922c55b76d504f4e9d32ab72805e4572e2e4b"},"schema_version":"1.0","source":{"id":"2203.02944","kind":"arxiv","version":1}},"canonical_sha256":"d60f0273e25d0213b86542331b764c198ec874def6ea5470022330ccf83b8be3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d60f0273e25d0213b86542331b764c198ec874def6ea5470022330ccf83b8be3","first_computed_at":"2026-07-05T04:02:29.288089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:02:29.288089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7JBk3JluNAQSkgvk4AZkPJTpdRsYiOkerY93/kbRaPg8mjR95Pq30KImZ7hlTavEe3weRLKgUxGVO8ZzhYDdDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:02:29.288487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a64d6cde542476844c3d236cafedaad6f334ba4a6ff09391faf3d428b873ee84","sha256:fb9d1279161104d67931a1fce559bd68b1b71635c3d1a732d7e335c22f9d0072"],"state_sha256":"56127301be3c4f61a38ae332cae460aadd4e022f75ab3aab58f167d3b19cbb76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uJLxFxJIpCYRdTwT9BOIuWBGjxxCDo9nI9WVOezbd3rSGFBEkvxQYB25UaWNrlxE8EgP7nUTnQcbhzOtxbgDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:23:17.579661Z","bundle_sha256":"ec8871d315d0e9a7c1fc848ed8d6a5f5cdddb2b88292c5a562f59cfd6637a426"}}