{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YQ22DCHL2T3QW4UEZQZJFDKUZ2","short_pith_number":"pith:YQ22DCHL","schema_version":"1.0","canonical_sha256":"c435a188ebd4f70b7284cc32928d54cea4a96352a28608c1c953898d42f2c8ba","source":{"kind":"arxiv","id":"2010.13154","version":2},"attestation_state":"computed","paper":{"title":"Attention is All You Need in Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Cem Subakan, Jianyuan Zhong, Mirco Ravanelli, Mirko Bronzi, Samuele Cornell","submitted_at":"2020-10-25T16:28:54Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) have long been the dominant architecture in sequence-to-sequence learning. RNNs, however, are inherently sequential models that do not allow parallelization of their computations. Transformers are emerging as a natural alternative to standard RNNs, replacing recurrent computations with a multi-head attention mechanism. In this paper, we propose the SepFormer, a novel RNN-free Transformer-based neural network for speech separation. The SepFormer learns short and long-term dependencies with a multi-scale approach that employs transformers. The proposed model achi"},"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":"2010.13154","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-25T16:28:54Z","cross_cats_sorted":["cs.LG","cs.SD","eess.SP"],"title_canon_sha256":"ad1f89ef2554d6a9b0f155cec2da3b3a46964b7ac6715c07730f66660c0ded23","abstract_canon_sha256":"0813f092ca7b326348adfc72cf3689dcfbef06316466e578dcc1ccc0bd0aadb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:18.139786Z","signature_b64":"+GaMnZosV6/chVxb9jWPE2vYrgsPo9x2Pugf9mxdV2yMp6BY7zcNHpd9E+acNBaGcyJhltnIEtoBqLnoHvsgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c435a188ebd4f70b7284cc32928d54cea4a96352a28608c1c953898d42f2c8ba","last_reissued_at":"2026-07-05T02:21:18.139278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:18.139278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention is All You Need in Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Cem Subakan, Jianyuan Zhong, Mirco Ravanelli, Mirko Bronzi, Samuele Cornell","submitted_at":"2020-10-25T16:28:54Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) have long been the dominant architecture in sequence-to-sequence learning. RNNs, however, are inherently sequential models that do not allow parallelization of their computations. Transformers are emerging as a natural alternative to standard RNNs, replacing recurrent computations with a multi-head attention mechanism. In this paper, we propose the SepFormer, a novel RNN-free Transformer-based neural network for speech separation. The SepFormer learns short and long-term dependencies with a multi-scale approach that employs transformers. The proposed model achi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13154","kind":"arxiv","version":2},"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/2010.13154/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":"2010.13154","created_at":"2026-07-05T02:21:18.139341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.13154v2","created_at":"2026-07-05T02:21:18.139341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13154","created_at":"2026-07-05T02:21:18.139341+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQ22DCHL2T3Q","created_at":"2026-07-05T02:21:18.139341+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQ22DCHL2T3QW4UE","created_at":"2026-07-05T02:21:18.139341+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQ22DCHL","created_at":"2026-07-05T02:21:18.139341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08375","citing_title":"Developing an Effective Training Dataset to Enhance the Performance of AI-based Speaker Separation Systems","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQ22DCHL2T3QW4UEZQZJFDKUZ2","json":"https://pith.science/pith/YQ22DCHL2T3QW4UEZQZJFDKUZ2.json","graph_json":"https://pith.science/api/pith-number/YQ22DCHL2T3QW4UEZQZJFDKUZ2/graph.json","events_json":"https://pith.science/api/pith-number/YQ22DCHL2T3QW4UEZQZJFDKUZ2/events.json","paper":"https://pith.science/paper/YQ22DCHL"},"agent_actions":{"view_html":"https://pith.science/pith/YQ22DCHL2T3QW4UEZQZJFDKUZ2","download_json":"https://pith.science/pith/YQ22DCHL2T3QW4UEZQZJFDKUZ2.json","view_paper":"https://pith.science/paper/YQ22DCHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.13154&json=true","fetch_graph":"https://pith.science/api/pith-number/YQ22DCHL2T3QW4UEZQZJFDKUZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/YQ22DCHL2T3QW4UEZQZJFDKUZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQ22DCHL2T3QW4UEZQZJFDKUZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQ22DCHL2T3QW4UEZQZJFDKUZ2/action/storage_attestation","attest_author":"https://pith.science/pith/YQ22DCHL2T3QW4UEZQZJFDKUZ2/action/author_attestation","sign_citation":"https://pith.science/pith/YQ22DCHL2T3QW4UEZQZJFDKUZ2/action/citation_signature","submit_replication":"https://pith.science/pith/YQ22DCHL2T3QW4UEZQZJFDKUZ2/action/replication_record"}},"created_at":"2026-07-05T02:21:18.139341+00:00","updated_at":"2026-07-05T02:21:18.139341+00:00"}