{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:L42RI7FT7NSVLLBVIOOH6Z5363","short_pith_number":"pith:L42RI7FT","schema_version":"1.0","canonical_sha256":"5f35147cb3fb6555ac35439c7f67bbf6fae31ba3894a12147d5dbe688754367b","source":{"kind":"arxiv","id":"1708.09588","version":1},"attestation_state":"computed","paper":{"title":"Joint Separation and Denoising of Noisy Multi-talker Speech using Recurrent Neural Networks and Permutation Invariant Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dong Yu, Jesper Jensen, Morten Kolb{\\ae}k, Zheng-Hua Tan","submitted_at":"2017-08-31T07:01:21Z","abstract_excerpt":"In this paper we propose to use utterance-level Permutation Invariant Training (uPIT) for speaker independent multi-talker speech separation and denoising, simultaneously. Specifically, we train deep bi-directional Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) using uPIT, for single-channel speaker independent multi-talker speech separation in multiple noisy conditions, including both synthetic and real-life noise signals. We focus our experiments on generalizability and noise robustness of models that rely on various types of a priori knowledge e.g. in terms of noise type and"},"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":"1708.09588","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-08-31T07:01:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"efb2a96f7152613397c0df01e4d218ab89a6e0186c7d2c821000798a6c16610c","abstract_canon_sha256":"a57b2abc48c02c90cf708f9164851afa6bf096cc308dc47888305124969a310a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:03.706091Z","signature_b64":"dpEU/Iw1klizrjSbXCNNp82Bm4TpNbW8Rb7emTkVIDo5B4X0VOVmXSNa3pv0SIkc7OyaRrLxcCAbVhVvXXvAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f35147cb3fb6555ac35439c7f67bbf6fae31ba3894a12147d5dbe688754367b","last_reissued_at":"2026-05-17T23:59:03.705718Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:03.705718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Separation and Denoising of Noisy Multi-talker Speech using Recurrent Neural Networks and Permutation Invariant Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dong Yu, Jesper Jensen, Morten Kolb{\\ae}k, Zheng-Hua Tan","submitted_at":"2017-08-31T07:01:21Z","abstract_excerpt":"In this paper we propose to use utterance-level Permutation Invariant Training (uPIT) for speaker independent multi-talker speech separation and denoising, simultaneously. Specifically, we train deep bi-directional Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) using uPIT, for single-channel speaker independent multi-talker speech separation in multiple noisy conditions, including both synthetic and real-life noise signals. We focus our experiments on generalizability and noise robustness of models that rely on various types of a priori knowledge e.g. in terms of noise type and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.09588","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":""},"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":"1708.09588","created_at":"2026-05-17T23:59:03.705775+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.09588v1","created_at":"2026-05-17T23:59:03.705775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.09588","created_at":"2026-05-17T23:59:03.705775+00:00"},{"alias_kind":"pith_short_12","alias_value":"L42RI7FT7NSV","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"L42RI7FT7NSVLLBV","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"L42RI7FT","created_at":"2026-05-18T12:31:28.150371+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/L42RI7FT7NSVLLBVIOOH6Z5363","json":"https://pith.science/pith/L42RI7FT7NSVLLBVIOOH6Z5363.json","graph_json":"https://pith.science/api/pith-number/L42RI7FT7NSVLLBVIOOH6Z5363/graph.json","events_json":"https://pith.science/api/pith-number/L42RI7FT7NSVLLBVIOOH6Z5363/events.json","paper":"https://pith.science/paper/L42RI7FT"},"agent_actions":{"view_html":"https://pith.science/pith/L42RI7FT7NSVLLBVIOOH6Z5363","download_json":"https://pith.science/pith/L42RI7FT7NSVLLBVIOOH6Z5363.json","view_paper":"https://pith.science/paper/L42RI7FT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.09588&json=true","fetch_graph":"https://pith.science/api/pith-number/L42RI7FT7NSVLLBVIOOH6Z5363/graph.json","fetch_events":"https://pith.science/api/pith-number/L42RI7FT7NSVLLBVIOOH6Z5363/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L42RI7FT7NSVLLBVIOOH6Z5363/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L42RI7FT7NSVLLBVIOOH6Z5363/action/storage_attestation","attest_author":"https://pith.science/pith/L42RI7FT7NSVLLBVIOOH6Z5363/action/author_attestation","sign_citation":"https://pith.science/pith/L42RI7FT7NSVLLBVIOOH6Z5363/action/citation_signature","submit_replication":"https://pith.science/pith/L42RI7FT7NSVLLBVIOOH6Z5363/action/replication_record"}},"created_at":"2026-05-17T23:59:03.705775+00:00","updated_at":"2026-05-17T23:59:03.705775+00:00"}