{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3DXIM4R7U7QJ6YIPVVFRWRTEDA","short_pith_number":"pith:3DXIM4R7","schema_version":"1.0","canonical_sha256":"d8ee86723fa7e09f610fad4b1b46641819fca8a98c1c9e46df0f0ea627a26fda","source":{"kind":"arxiv","id":"2107.11066","version":1},"attestation_state":"computed","paper":{"title":"SALADnet: Self-Attentive multisource Localization in the Ambisonics Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexandre Gu\\'erin, Laurent Girin, Pierre-Amaury Grumiaux, Prerak Srivastava, Srdan Kitic","submitted_at":"2021-07-23T08:14:09Z","abstract_excerpt":"In this work, we propose a novel self-attention based neural network for robust multi-speaker localization from Ambisonics recordings. Starting from a state-of-the-art convolutional recurrent neural network, we investigate the benefit of replacing the recurrent layers by self-attention encoders, inherited from the Transformer architecture. We evaluate these models on synthetic and real-world data, with up to 3 simultaneous speakers. The obtained results indicate that the majority of the proposed architectures either perform on par, or outperform the CRNN baseline, especially in the multisource"},"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":"2107.11066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-07-23T08:14:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"026af39eec59feb5125fbe281b61ac7015de59bb764b05a273e4f03cbcebd195","abstract_canon_sha256":"129cd91825efeb182b9b385b881b47d2a487f50376cdf2f301f29d94ed889d25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:12.944448Z","signature_b64":"FIPF0ZEQVGqVfvpMpNwF6e5V4YERmrcnHQkOXTocoGtJiqZLVaLl0TtVbpRiCk5dg9Xbs9ISREmNyddunkskAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8ee86723fa7e09f610fad4b1b46641819fca8a98c1c9e46df0f0ea627a26fda","last_reissued_at":"2026-07-05T03:00:12.944059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:12.944059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SALADnet: Self-Attentive multisource Localization in the Ambisonics Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexandre Gu\\'erin, Laurent Girin, Pierre-Amaury Grumiaux, Prerak Srivastava, Srdan Kitic","submitted_at":"2021-07-23T08:14:09Z","abstract_excerpt":"In this work, we propose a novel self-attention based neural network for robust multi-speaker localization from Ambisonics recordings. Starting from a state-of-the-art convolutional recurrent neural network, we investigate the benefit of replacing the recurrent layers by self-attention encoders, inherited from the Transformer architecture. We evaluate these models on synthetic and real-world data, with up to 3 simultaneous speakers. The obtained results indicate that the majority of the proposed architectures either perform on par, or outperform the CRNN baseline, especially in the multisource"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11066","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/2107.11066/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":"2107.11066","created_at":"2026-07-05T03:00:12.944111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.11066v1","created_at":"2026-07-05T03:00:12.944111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11066","created_at":"2026-07-05T03:00:12.944111+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DXIM4R7U7QJ","created_at":"2026-07-05T03:00:12.944111+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DXIM4R7U7QJ6YIP","created_at":"2026-07-05T03:00:12.944111+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DXIM4R7","created_at":"2026-07-05T03:00:12.944111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DXIM4R7U7QJ6YIPVVFRWRTEDA","json":"https://pith.science/pith/3DXIM4R7U7QJ6YIPVVFRWRTEDA.json","graph_json":"https://pith.science/api/pith-number/3DXIM4R7U7QJ6YIPVVFRWRTEDA/graph.json","events_json":"https://pith.science/api/pith-number/3DXIM4R7U7QJ6YIPVVFRWRTEDA/events.json","paper":"https://pith.science/paper/3DXIM4R7"},"agent_actions":{"view_html":"https://pith.science/pith/3DXIM4R7U7QJ6YIPVVFRWRTEDA","download_json":"https://pith.science/pith/3DXIM4R7U7QJ6YIPVVFRWRTEDA.json","view_paper":"https://pith.science/paper/3DXIM4R7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.11066&json=true","fetch_graph":"https://pith.science/api/pith-number/3DXIM4R7U7QJ6YIPVVFRWRTEDA/graph.json","fetch_events":"https://pith.science/api/pith-number/3DXIM4R7U7QJ6YIPVVFRWRTEDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DXIM4R7U7QJ6YIPVVFRWRTEDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DXIM4R7U7QJ6YIPVVFRWRTEDA/action/storage_attestation","attest_author":"https://pith.science/pith/3DXIM4R7U7QJ6YIPVVFRWRTEDA/action/author_attestation","sign_citation":"https://pith.science/pith/3DXIM4R7U7QJ6YIPVVFRWRTEDA/action/citation_signature","submit_replication":"https://pith.science/pith/3DXIM4R7U7QJ6YIPVVFRWRTEDA/action/replication_record"}},"created_at":"2026-07-05T03:00:12.944111+00:00","updated_at":"2026-07-05T03:00:12.944111+00:00"}