{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FGSP3TEJOVUUREWFNHBJQQFM4A","short_pith_number":"pith:FGSP3TEJ","schema_version":"1.0","canonical_sha256":"29a4fdcc8975694892c569c29840ace00bd19825a96e56390457fd475762a8a0","source":{"kind":"arxiv","id":"2407.01857","version":1},"attestation_state":"computed","paper":{"title":"SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Atsushi Ando, Hiroshi Sato, Kentaro Shinayama, Marc Delcroix, Masato Mimura, Shota Horiguchi, Takafumi Moriya, Takanori Ashihara, Tsubasa Ochiai","submitted_at":"2024-07-01T23:59:16Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.01857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-01T23:59:16Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"a64324729b45386bcf99a504ced9b48c6ce9e118f3d21fc8cd06f2e685d2acb6","abstract_canon_sha256":"19f445333fc46691ba15bf2412bb17f436d53494e9e78a34c2b762cc198768bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:06.276958Z","signature_b64":"Kx3ffbryr9KRpVTSxKetKaBpr9QnUjFfDdDsjIx1k2+rzVfTbV2x1Z57oEJ6symz5QKhkomC31kHiTcOcMP3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29a4fdcc8975694892c569c29840ace00bd19825a96e56390457fd475762a8a0","last_reissued_at":"2026-07-05T08:39:06.276482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:06.276482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Atsushi Ando, Hiroshi Sato, Kentaro Shinayama, Marc Delcroix, Masato Mimura, Shota Horiguchi, Takafumi Moriya, Takanori Ashihara, Tsubasa Ochiai","submitted_at":"2024-07-01T23:59:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01857","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/2407.01857/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.01857","created_at":"2026-07-05T08:39:06.276565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01857v1","created_at":"2026-07-05T08:39:06.276565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01857","created_at":"2026-07-05T08:39:06.276565+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGSP3TEJOVUU","created_at":"2026-07-05T08:39:06.276565+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGSP3TEJOVUUREWF","created_at":"2026-07-05T08:39:06.276565+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGSP3TEJ","created_at":"2026-07-05T08:39:06.276565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23332","citing_title":"Don't Listen to Me: A Lightweight, Low-Latency Model for Own-Voice Cancellation in Far-Field Speech Enhancement","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FGSP3TEJOVUUREWFNHBJQQFM4A","json":"https://pith.science/pith/FGSP3TEJOVUUREWFNHBJQQFM4A.json","graph_json":"https://pith.science/api/pith-number/FGSP3TEJOVUUREWFNHBJQQFM4A/graph.json","events_json":"https://pith.science/api/pith-number/FGSP3TEJOVUUREWFNHBJQQFM4A/events.json","paper":"https://pith.science/paper/FGSP3TEJ"},"agent_actions":{"view_html":"https://pith.science/pith/FGSP3TEJOVUUREWFNHBJQQFM4A","download_json":"https://pith.science/pith/FGSP3TEJOVUUREWFNHBJQQFM4A.json","view_paper":"https://pith.science/paper/FGSP3TEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01857&json=true","fetch_graph":"https://pith.science/api/pith-number/FGSP3TEJOVUUREWFNHBJQQFM4A/graph.json","fetch_events":"https://pith.science/api/pith-number/FGSP3TEJOVUUREWFNHBJQQFM4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGSP3TEJOVUUREWFNHBJQQFM4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGSP3TEJOVUUREWFNHBJQQFM4A/action/storage_attestation","attest_author":"https://pith.science/pith/FGSP3TEJOVUUREWFNHBJQQFM4A/action/author_attestation","sign_citation":"https://pith.science/pith/FGSP3TEJOVUUREWFNHBJQQFM4A/action/citation_signature","submit_replication":"https://pith.science/pith/FGSP3TEJOVUUREWFNHBJQQFM4A/action/replication_record"}},"created_at":"2026-07-05T08:39:06.276565+00:00","updated_at":"2026-07-05T08:39:06.276565+00:00"}