{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CBFNN7PRJV3AR7X264UNUWXKMR","short_pith_number":"pith:CBFNN7PR","schema_version":"1.0","canonical_sha256":"104ad6fdf14d7608fefaf728da5aea6446184a666320a010b3cd177693ff3974","source":{"kind":"arxiv","id":"1709.03658","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"stat.ML","authors_text":"Hisashi Kawai, Szu-Wei Fu, Tao-Wei Wang, Xugang Lu, Yu Tsao","submitted_at":"2017-09-12T02:24:50Z","abstract_excerpt":"Speech enhancement model is used to map a noisy speech to a clean speech. In the training stage, an objective function is often adopted to optimize the model parameters. However, in most studies, there is an inconsistency between the model optimization criterion and the evaluation criterion on the enhanced speech. For example, in measuring speech intelligibility, most of the evaluation metric is based on a short-time objective intelligibility (STOI) measure, while the frame based minimum mean square error (MMSE) between estimated and clean speech is widely used in optimizing the model. Due to "},"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":"1709.03658","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-12T02:24:50Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"d1d38b43c28e44b041300f21a4f44bdacb89eb23bb87f144b569b8602803e22e","abstract_canon_sha256":"b8cae2e55b461cd14345c1bb431ffeebf276d8276fdd454e46d3a5770741b90b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:56.247889Z","signature_b64":"pHmKRhYUqcbzbkhOOf5hAL5F+3SDxeoLmBIuxn6Dzdag++k1HylLQ4ij9Au+vyzmNpHxG/yjNIVLqT7TozbVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"104ad6fdf14d7608fefaf728da5aea6446184a666320a010b3cd177693ff3974","last_reissued_at":"2026-05-18T00:20:56.247350Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:56.247350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"stat.ML","authors_text":"Hisashi Kawai, Szu-Wei Fu, Tao-Wei Wang, Xugang Lu, Yu Tsao","submitted_at":"2017-09-12T02:24:50Z","abstract_excerpt":"Speech enhancement model is used to map a noisy speech to a clean speech. In the training stage, an objective function is often adopted to optimize the model parameters. However, in most studies, there is an inconsistency between the model optimization criterion and the evaluation criterion on the enhanced speech. For example, in measuring speech intelligibility, most of the evaluation metric is based on a short-time objective intelligibility (STOI) measure, while the frame based minimum mean square error (MMSE) between estimated and clean speech is widely used in optimizing the model. Due to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03658","kind":"arxiv","version":2},"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":"1709.03658","created_at":"2026-05-18T00:20:56.247417+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.03658v2","created_at":"2026-05-18T00:20:56.247417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03658","created_at":"2026-05-18T00:20:56.247417+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBFNN7PRJV3A","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBFNN7PRJV3AR7X2","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBFNN7PR","created_at":"2026-05-18T12:31:10.602751+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/CBFNN7PRJV3AR7X264UNUWXKMR","json":"https://pith.science/pith/CBFNN7PRJV3AR7X264UNUWXKMR.json","graph_json":"https://pith.science/api/pith-number/CBFNN7PRJV3AR7X264UNUWXKMR/graph.json","events_json":"https://pith.science/api/pith-number/CBFNN7PRJV3AR7X264UNUWXKMR/events.json","paper":"https://pith.science/paper/CBFNN7PR"},"agent_actions":{"view_html":"https://pith.science/pith/CBFNN7PRJV3AR7X264UNUWXKMR","download_json":"https://pith.science/pith/CBFNN7PRJV3AR7X264UNUWXKMR.json","view_paper":"https://pith.science/paper/CBFNN7PR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.03658&json=true","fetch_graph":"https://pith.science/api/pith-number/CBFNN7PRJV3AR7X264UNUWXKMR/graph.json","fetch_events":"https://pith.science/api/pith-number/CBFNN7PRJV3AR7X264UNUWXKMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBFNN7PRJV3AR7X264UNUWXKMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBFNN7PRJV3AR7X264UNUWXKMR/action/storage_attestation","attest_author":"https://pith.science/pith/CBFNN7PRJV3AR7X264UNUWXKMR/action/author_attestation","sign_citation":"https://pith.science/pith/CBFNN7PRJV3AR7X264UNUWXKMR/action/citation_signature","submit_replication":"https://pith.science/pith/CBFNN7PRJV3AR7X264UNUWXKMR/action/replication_record"}},"created_at":"2026-05-18T00:20:56.247417+00:00","updated_at":"2026-05-18T00:20:56.247417+00:00"}