{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GIAIQMLYFWXIUMZBBRVEKZTRVB","short_pith_number":"pith:GIAIQMLY","schema_version":"1.0","canonical_sha256":"32008831782dae8a33210c6a456671a859a6a9e71453ac5dba148060ad2692f5","source":{"kind":"arxiv","id":"2007.13975","version":3},"attestation_state":"computed","paper":{"title":"Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dong Liu, Jingjing Chen, Qirong Mao","submitted_at":"2020-07-28T03:51:28Z","abstract_excerpt":"The dominant speech separation models are based on complex recurrent or convolution neural network that model speech sequences indirectly conditioning on context, such as passing information through many intermediate states in recurrent neural network, leading to suboptimal separation performance. In this paper, we propose a dual-path transformer network (DPTNet) for end-to-end speech separation, which introduces direct context-awareness in the modeling for speech sequences. By introduces a improved transformer, elements in speech sequences can interact directly, which enables DPTNet can model"},"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":"2007.13975","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-28T03:51:28Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"2a1c208dd9dafc762dfef6a92e902f12d5a8cdaa9a7b4fee9a3445e98a612418","abstract_canon_sha256":"4ad83dbe5b645f13a9993f386d4f096a75ac113d608e17db882a868ccfed2557"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:04.457995Z","signature_b64":"aAWJ7Pbmp8DV0+F9xSZAS/ex85elFDXw0X23vsrnuSC+Lz0ThVEND2KEi+VtZCcFiHPbCzifg1yxZauVcpk3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32008831782dae8a33210c6a456671a859a6a9e71453ac5dba148060ad2692f5","last_reissued_at":"2026-07-05T01:27:04.457534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:04.457534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dong Liu, Jingjing Chen, Qirong Mao","submitted_at":"2020-07-28T03:51:28Z","abstract_excerpt":"The dominant speech separation models are based on complex recurrent or convolution neural network that model speech sequences indirectly conditioning on context, such as passing information through many intermediate states in recurrent neural network, leading to suboptimal separation performance. In this paper, we propose a dual-path transformer network (DPTNet) for end-to-end speech separation, which introduces direct context-awareness in the modeling for speech sequences. By introduces a improved transformer, elements in speech sequences can interact directly, which enables DPTNet can model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13975","kind":"arxiv","version":3},"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/2007.13975/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":"2007.13975","created_at":"2026-07-05T01:27:04.457589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.13975v3","created_at":"2026-07-05T01:27:04.457589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13975","created_at":"2026-07-05T01:27:04.457589+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIAIQMLYFWXI","created_at":"2026-07-05T01:27:04.457589+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIAIQMLYFWXIUMZB","created_at":"2026-07-05T01:27:04.457589+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIAIQMLY","created_at":"2026-07-05T01:27:04.457589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.06006","citing_title":"Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11717","citing_title":"CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIAIQMLYFWXIUMZBBRVEKZTRVB","json":"https://pith.science/pith/GIAIQMLYFWXIUMZBBRVEKZTRVB.json","graph_json":"https://pith.science/api/pith-number/GIAIQMLYFWXIUMZBBRVEKZTRVB/graph.json","events_json":"https://pith.science/api/pith-number/GIAIQMLYFWXIUMZBBRVEKZTRVB/events.json","paper":"https://pith.science/paper/GIAIQMLY"},"agent_actions":{"view_html":"https://pith.science/pith/GIAIQMLYFWXIUMZBBRVEKZTRVB","download_json":"https://pith.science/pith/GIAIQMLYFWXIUMZBBRVEKZTRVB.json","view_paper":"https://pith.science/paper/GIAIQMLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.13975&json=true","fetch_graph":"https://pith.science/api/pith-number/GIAIQMLYFWXIUMZBBRVEKZTRVB/graph.json","fetch_events":"https://pith.science/api/pith-number/GIAIQMLYFWXIUMZBBRVEKZTRVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIAIQMLYFWXIUMZBBRVEKZTRVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIAIQMLYFWXIUMZBBRVEKZTRVB/action/storage_attestation","attest_author":"https://pith.science/pith/GIAIQMLYFWXIUMZBBRVEKZTRVB/action/author_attestation","sign_citation":"https://pith.science/pith/GIAIQMLYFWXIUMZBBRVEKZTRVB/action/citation_signature","submit_replication":"https://pith.science/pith/GIAIQMLYFWXIUMZBBRVEKZTRVB/action/replication_record"}},"created_at":"2026-07-05T01:27:04.457589+00:00","updated_at":"2026-07-05T01:27:04.457589+00:00"}