{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4ZZ6EO7PVEUKROQUPR7I6ZCU3Y","short_pith_number":"pith:4ZZ6EO7P","schema_version":"1.0","canonical_sha256":"e673e23befa928a8ba147c7e8f6454de160b12d3d9d690527a6f9a36b7b3fcf2","source":{"kind":"arxiv","id":"1903.09952","version":1},"attestation_state":"computed","paper":{"title":"Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenglin Xu, Eng Siong Chng, Haizhou Li, Wei Rao","submitted_at":"2019-03-24T09:25:26Z","abstract_excerpt":"The SpeakerBeam-FE (SBF) method is proposed for speaker extraction. It attempts to overcome the problem of unknown number of speakers in an audio recording during source separation. The mask approximation loss of SBF is sub-optimal, which doesn't calculate direct signal reconstruction error and consider the speech context. To address these problems, this paper proposes a magnitude and temporal spectrum approximation loss to estimate a phase sensitive mask for the target speaker with the speaker characteristics. Moreover, this paper explores a concatenation framework instead of the context adap"},"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":"1903.09952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-03-24T09:25:26Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"e9a00a83948441404033f7db58083f6788a589298029e9ae4ab5b3826eb31404","abstract_canon_sha256":"c56ff54d648c691a57399090905693a7404cb4a0ca4f3acef3a507debbcd9441"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:34.957893Z","signature_b64":"yqKOYlk8v3ytFkJbDtR9DkvCldIIgIVX9C5nqx6Z4TiUfLnRPEp5Uz1VC9TVVYIG5FvCtibtW6amfYmBWVOXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e673e23befa928a8ba147c7e8f6454de160b12d3d9d690527a6f9a36b7b3fcf2","last_reissued_at":"2026-05-17T23:50:34.957080Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:34.957080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenglin Xu, Eng Siong Chng, Haizhou Li, Wei Rao","submitted_at":"2019-03-24T09:25:26Z","abstract_excerpt":"The SpeakerBeam-FE (SBF) method is proposed for speaker extraction. It attempts to overcome the problem of unknown number of speakers in an audio recording during source separation. The mask approximation loss of SBF is sub-optimal, which doesn't calculate direct signal reconstruction error and consider the speech context. To address these problems, this paper proposes a magnitude and temporal spectrum approximation loss to estimate a phase sensitive mask for the target speaker with the speaker characteristics. Moreover, this paper explores a concatenation framework instead of the context adap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09952","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":"1903.09952","created_at":"2026-05-17T23:50:34.957218+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.09952v1","created_at":"2026-05-17T23:50:34.957218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09952","created_at":"2026-05-17T23:50:34.957218+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZZ6EO7PVEUK","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZZ6EO7PVEUKROQU","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZZ6EO7P","created_at":"2026-05-18T12:33:10.108867+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/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y","json":"https://pith.science/pith/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y.json","graph_json":"https://pith.science/api/pith-number/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y/graph.json","events_json":"https://pith.science/api/pith-number/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y/events.json","paper":"https://pith.science/paper/4ZZ6EO7P"},"agent_actions":{"view_html":"https://pith.science/pith/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y","download_json":"https://pith.science/pith/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y.json","view_paper":"https://pith.science/paper/4ZZ6EO7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.09952&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y/action/storage_attestation","attest_author":"https://pith.science/pith/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y/action/author_attestation","sign_citation":"https://pith.science/pith/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y/action/citation_signature","submit_replication":"https://pith.science/pith/4ZZ6EO7PVEUKROQUPR7I6ZCU3Y/action/replication_record"}},"created_at":"2026-05-17T23:50:34.957218+00:00","updated_at":"2026-05-17T23:50:34.957218+00:00"}