{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZV7SL6OQRCZCA6JV3KMY3ESYUI","short_pith_number":"pith:ZV7SL6OQ","schema_version":"1.0","canonical_sha256":"cd7f25f9d088b2207935da998d9258a231fe524cc46669af5b329d57ea3d59a2","source":{"kind":"arxiv","id":"1907.04984","version":1},"attestation_state":"computed","paper":{"title":"Multichannel Loss Function for Supervised Speech Source Separation by Mask-based Beamforming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Masahito Togami, Tatsuya Komatsu, Yoshiki Masuyama","submitted_at":"2019-07-11T03:41:20Z","abstract_excerpt":"In this paper, we propose two mask-based beamforming methods using a deep neural network (DNN) trained by multichannel loss functions. Beamforming technique using time-frequency (TF)-masks estimated by a DNN have been applied to many applications where TF-masks are used for estimating spatial covariance matrices. To train a DNN for mask-based beamforming, loss functions designed for monaural speech enhancement/separation have been employed. Although such a training criterion is simple, it does not directly correspond to the performance of mask-based beamforming. To overcome this problem, we us"},"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":"1907.04984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-07-11T03:41:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"266fdbca72a48042b8180ebc8a44394c7daf276364a1df7dd9652df15f8aa512","abstract_canon_sha256":"a83d32eb5834c48b4f355420511b71e67e07f6cf4fedfeb9649926604e6cee34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:54.287337Z","signature_b64":"oeI7anDZsr2O/r2ZBN6CLT/qF8vunlBReAHOr1qF8lS7SbYLGOs/8yQtSR3hE2pvZpiGBpp49CHlgaeLHpotCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd7f25f9d088b2207935da998d9258a231fe524cc46669af5b329d57ea3d59a2","last_reissued_at":"2026-05-17T23:40:54.286714Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:54.286714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multichannel Loss Function for Supervised Speech Source Separation by Mask-based Beamforming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Masahito Togami, Tatsuya Komatsu, Yoshiki Masuyama","submitted_at":"2019-07-11T03:41:20Z","abstract_excerpt":"In this paper, we propose two mask-based beamforming methods using a deep neural network (DNN) trained by multichannel loss functions. Beamforming technique using time-frequency (TF)-masks estimated by a DNN have been applied to many applications where TF-masks are used for estimating spatial covariance matrices. To train a DNN for mask-based beamforming, loss functions designed for monaural speech enhancement/separation have been employed. Although such a training criterion is simple, it does not directly correspond to the performance of mask-based beamforming. To overcome this problem, we us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04984","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":"1907.04984","created_at":"2026-05-17T23:40:54.286799+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04984v1","created_at":"2026-05-17T23:40:54.286799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04984","created_at":"2026-05-17T23:40:54.286799+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZV7SL6OQRCZC","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZV7SL6OQRCZCA6JV","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZV7SL6OQ","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04984","citing_title":"Multichannel Loss Function for Supervised Speech Source Separation by Mask-based Beamforming","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZV7SL6OQRCZCA6JV3KMY3ESYUI","json":"https://pith.science/pith/ZV7SL6OQRCZCA6JV3KMY3ESYUI.json","graph_json":"https://pith.science/api/pith-number/ZV7SL6OQRCZCA6JV3KMY3ESYUI/graph.json","events_json":"https://pith.science/api/pith-number/ZV7SL6OQRCZCA6JV3KMY3ESYUI/events.json","paper":"https://pith.science/paper/ZV7SL6OQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZV7SL6OQRCZCA6JV3KMY3ESYUI","download_json":"https://pith.science/pith/ZV7SL6OQRCZCA6JV3KMY3ESYUI.json","view_paper":"https://pith.science/paper/ZV7SL6OQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04984&json=true","fetch_graph":"https://pith.science/api/pith-number/ZV7SL6OQRCZCA6JV3KMY3ESYUI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZV7SL6OQRCZCA6JV3KMY3ESYUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZV7SL6OQRCZCA6JV3KMY3ESYUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZV7SL6OQRCZCA6JV3KMY3ESYUI/action/storage_attestation","attest_author":"https://pith.science/pith/ZV7SL6OQRCZCA6JV3KMY3ESYUI/action/author_attestation","sign_citation":"https://pith.science/pith/ZV7SL6OQRCZCA6JV3KMY3ESYUI/action/citation_signature","submit_replication":"https://pith.science/pith/ZV7SL6OQRCZCA6JV3KMY3ESYUI/action/replication_record"}},"created_at":"2026-05-17T23:40:54.286799+00:00","updated_at":"2026-05-17T23:40:54.286799+00:00"}