{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FGSP3TEJOVUUREWFNHBJQQFM4A","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":"19f445333fc46691ba15bf2412bb17f436d53494e9e78a34c2b762cc198768bf","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-01T23:59:16Z","title_canon_sha256":"a64324729b45386bcf99a504ced9b48c6ce9e118f3d21fc8cd06f2e685d2acb6"},"schema_version":"1.0","source":{"id":"2407.01857","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01857","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01857v1","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01857","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"FGSP3TEJOVUU","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"FGSP3TEJOVUUREWF","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"FGSP3TEJ","created_at":"2026-07-05T08:39:06Z"}],"graph_snapshots":[{"event_id":"sha256:e1d1e3ad4ccb433929466f49fe8543278017280359e9670f3dd7ee34c2be371c","target":"graph","created_at":"2026-07-05T08:39:06Z","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/2407.01857/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-time target speaker extraction (TSE) is intended to extract the desired speaker's voice from the observed mixture of multiple speakers in a streaming manner. Implementing real-time TSE is challenging as the computational complexity must be reduced to provide real-time operation. This work introduces to Conv-TasNet-based TSE a new architecture based on state space modeling (SSM) that has been shown to model long-term dependency effectively. Owing to SSM, fewer dilated convolutional layers are required to capture temporal dependency in Conv-TasNet, resulting in the reduction of model comple","authors_text":"Atsushi Ando, Hiroshi Sato, Kentaro Shinayama, Marc Delcroix, Masato Mimura, Shota Horiguchi, Takafumi Moriya, Takanori Ashihara, Tsubasa Ochiai","cross_cats":["cs.SD","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-01T23:59:16Z","title":"SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01857","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:aae85c3dec8f5478cd186826f9a196de4b4b6c277696bb6ffbffc2f19764cd11","target":"record","created_at":"2026-07-05T08:39:06Z","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":"19f445333fc46691ba15bf2412bb17f436d53494e9e78a34c2b762cc198768bf","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-01T23:59:16Z","title_canon_sha256":"a64324729b45386bcf99a504ced9b48c6ce9e118f3d21fc8cd06f2e685d2acb6"},"schema_version":"1.0","source":{"id":"2407.01857","kind":"arxiv","version":1}},"canonical_sha256":"29a4fdcc8975694892c569c29840ace00bd19825a96e56390457fd475762a8a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29a4fdcc8975694892c569c29840ace00bd19825a96e56390457fd475762a8a0","first_computed_at":"2026-07-05T08:39:06.276482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:06.276482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kx3ffbryr9KRpVTSxKetKaBpr9QnUjFfDdDsjIx1k2+rzVfTbV2x1Z57oEJ6symz5QKhkomC31kHiTcOcMP3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:06.276958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01857","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aae85c3dec8f5478cd186826f9a196de4b4b6c277696bb6ffbffc2f19764cd11","sha256:e1d1e3ad4ccb433929466f49fe8543278017280359e9670f3dd7ee34c2be371c"],"state_sha256":"1f161c9a2093798ba6f5e0376e0351ecc7db551cc6125c8f627ecb69a768b91c"}