{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WDID5M4EPQCEXHK5LD74RYWLFU","short_pith_number":"pith:WDID5M4E","schema_version":"1.0","canonical_sha256":"b0d03eb3847c044b9d5d58ffc8e2cb2d02322950067fc112ab0aeed5afe55d6a","source":{"kind":"arxiv","id":"1807.06899","version":1},"attestation_state":"computed","paper":{"title":"Deep neural network based speech separation optimizing an objective estimator of intelligibility for low latency applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Gaurav Naithani, Joonas Nikunen, Lars Bramsl{\\o}w, Tuomas Virtanen","submitted_at":"2018-07-18T12:55:59Z","abstract_excerpt":"Mean square error (MSE) has been the preferred choice as loss function in the current deep neural network (DNN) based speech separation techniques. In this paper, we propose a new cost function with the aim of optimizing the extended short time objective intelligibility (ESTOI) measure. We focus on applications where low algorithmic latency ($\\leq 10$ ms) is important. We use long short-term memory networks (LSTM) and evaluate our proposed approach on four sets of two-speaker mixtures from extended Danish hearing in noise (HINT) dataset. We show that the proposed loss function can offer improv"},"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":"1807.06899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-07-18T12:55:59Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b5332051c930d9850fb96d726d134120d1fa42e7c651bb5f3268480d62e5d249","abstract_canon_sha256":"8cc40ac0ef82a44ac0e920274b1225f7879c60ea9fad1c96f95d664282c63f14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:25.394127Z","signature_b64":"CVU31NwTwyGrJ/6eOw6ku+pFlVJbGN1NyBtrVXy2QJYvOQZEFbLwj4ij04prMtmzBXzYFTxMQ5TaaBOoyGxlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0d03eb3847c044b9d5d58ffc8e2cb2d02322950067fc112ab0aeed5afe55d6a","last_reissued_at":"2026-05-18T00:10:25.393567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:25.393567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep neural network based speech separation optimizing an objective estimator of intelligibility for low latency applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Gaurav Naithani, Joonas Nikunen, Lars Bramsl{\\o}w, Tuomas Virtanen","submitted_at":"2018-07-18T12:55:59Z","abstract_excerpt":"Mean square error (MSE) has been the preferred choice as loss function in the current deep neural network (DNN) based speech separation techniques. In this paper, we propose a new cost function with the aim of optimizing the extended short time objective intelligibility (ESTOI) measure. We focus on applications where low algorithmic latency ($\\leq 10$ ms) is important. We use long short-term memory networks (LSTM) and evaluate our proposed approach on four sets of two-speaker mixtures from extended Danish hearing in noise (HINT) dataset. We show that the proposed loss function can offer improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06899","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":"1807.06899","created_at":"2026-05-18T00:10:25.393660+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06899v1","created_at":"2026-05-18T00:10:25.393660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06899","created_at":"2026-05-18T00:10:25.393660+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDID5M4EPQCE","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDID5M4EPQCEXHK5","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDID5M4E","created_at":"2026-05-18T12:32:59.047623+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/WDID5M4EPQCEXHK5LD74RYWLFU","json":"https://pith.science/pith/WDID5M4EPQCEXHK5LD74RYWLFU.json","graph_json":"https://pith.science/api/pith-number/WDID5M4EPQCEXHK5LD74RYWLFU/graph.json","events_json":"https://pith.science/api/pith-number/WDID5M4EPQCEXHK5LD74RYWLFU/events.json","paper":"https://pith.science/paper/WDID5M4E"},"agent_actions":{"view_html":"https://pith.science/pith/WDID5M4EPQCEXHK5LD74RYWLFU","download_json":"https://pith.science/pith/WDID5M4EPQCEXHK5LD74RYWLFU.json","view_paper":"https://pith.science/paper/WDID5M4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06899&json=true","fetch_graph":"https://pith.science/api/pith-number/WDID5M4EPQCEXHK5LD74RYWLFU/graph.json","fetch_events":"https://pith.science/api/pith-number/WDID5M4EPQCEXHK5LD74RYWLFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDID5M4EPQCEXHK5LD74RYWLFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDID5M4EPQCEXHK5LD74RYWLFU/action/storage_attestation","attest_author":"https://pith.science/pith/WDID5M4EPQCEXHK5LD74RYWLFU/action/author_attestation","sign_citation":"https://pith.science/pith/WDID5M4EPQCEXHK5LD74RYWLFU/action/citation_signature","submit_replication":"https://pith.science/pith/WDID5M4EPQCEXHK5LD74RYWLFU/action/replication_record"}},"created_at":"2026-05-18T00:10:25.393660+00:00","updated_at":"2026-05-18T00:10:25.393660+00:00"}