{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VJ5U4WAG4BPXRYDW6EMYBVGSF7","short_pith_number":"pith:VJ5U4WAG","schema_version":"1.0","canonical_sha256":"aa7b4e5806e05f78e076f11980d4d22fd0df5f1bd2d2cbfb3bc8da049aed46b7","source":{"kind":"arxiv","id":"2104.03538","version":2},"attestation_state":"computed","paper":{"title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Cheng Yu, Mirco Ravanelli, Peter Plantinga, Szu-Wei Fu, Tsun-An Hsieh, Xugang Lu, Yu Tsao","submitted_at":"2021-04-08T06:46:35Z","abstract_excerpt":"The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory. Objective evaluation metrics which consider human perception can hence serve as a bridge to reduce the gap. Our previously proposed MetricGAN was designed to optimize objective metrics by connecting the metric with a discriminator. Because only the scores of the target evaluation functions are needed during training, the metrics can even be non-differentiable. In this study, we propose a MetricGAN+ in which three train"},"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":"2104.03538","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-08T06:46:35Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"80672534d9e22ea3c593cb6d3c17a157104ebe1f7566724313febfd8da6f7931","abstract_canon_sha256":"fea26734e61355331b6c915cd81c6395a790eca82663705a6223732acb971d46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:13.036533Z","signature_b64":"Id4LIo/4540UsbUhAfxahWBOmNIEp/GuOr1pMxd4PukojCE4IjIHEx0YOFCdEFnfhC6dH9Rr8fAkKhptBfJBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa7b4e5806e05f78e076f11980d4d22fd0df5f1bd2d2cbfb3bc8da049aed46b7","last_reissued_at":"2026-07-05T02:46:13.036054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:13.036054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Cheng Yu, Mirco Ravanelli, Peter Plantinga, Szu-Wei Fu, Tsun-An Hsieh, Xugang Lu, Yu Tsao","submitted_at":"2021-04-08T06:46:35Z","abstract_excerpt":"The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory. Objective evaluation metrics which consider human perception can hence serve as a bridge to reduce the gap. Our previously proposed MetricGAN was designed to optimize objective metrics by connecting the metric with a discriminator. Because only the scores of the target evaluation functions are needed during training, the metrics can even be non-differentiable. In this study, we propose a MetricGAN+ in which three train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03538","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.03538/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2104.03538","created_at":"2026-07-05T02:46:13.036110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.03538v2","created_at":"2026-07-05T02:46:13.036110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03538","created_at":"2026-07-05T02:46:13.036110+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJ5U4WAG4BPX","created_at":"2026-07-05T02:46:13.036110+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJ5U4WAG4BPXRYDW","created_at":"2026-07-05T02:46:13.036110+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJ5U4WAG","created_at":"2026-07-05T02:46:13.036110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23139","citing_title":"Audio Editing in the Era of Foundation Models: A Survey","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJ5U4WAG4BPXRYDW6EMYBVGSF7","json":"https://pith.science/pith/VJ5U4WAG4BPXRYDW6EMYBVGSF7.json","graph_json":"https://pith.science/api/pith-number/VJ5U4WAG4BPXRYDW6EMYBVGSF7/graph.json","events_json":"https://pith.science/api/pith-number/VJ5U4WAG4BPXRYDW6EMYBVGSF7/events.json","paper":"https://pith.science/paper/VJ5U4WAG"},"agent_actions":{"view_html":"https://pith.science/pith/VJ5U4WAG4BPXRYDW6EMYBVGSF7","download_json":"https://pith.science/pith/VJ5U4WAG4BPXRYDW6EMYBVGSF7.json","view_paper":"https://pith.science/paper/VJ5U4WAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.03538&json=true","fetch_graph":"https://pith.science/api/pith-number/VJ5U4WAG4BPXRYDW6EMYBVGSF7/graph.json","fetch_events":"https://pith.science/api/pith-number/VJ5U4WAG4BPXRYDW6EMYBVGSF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJ5U4WAG4BPXRYDW6EMYBVGSF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJ5U4WAG4BPXRYDW6EMYBVGSF7/action/storage_attestation","attest_author":"https://pith.science/pith/VJ5U4WAG4BPXRYDW6EMYBVGSF7/action/author_attestation","sign_citation":"https://pith.science/pith/VJ5U4WAG4BPXRYDW6EMYBVGSF7/action/citation_signature","submit_replication":"https://pith.science/pith/VJ5U4WAG4BPXRYDW6EMYBVGSF7/action/replication_record"}},"created_at":"2026-07-05T02:46:13.036110+00:00","updated_at":"2026-07-05T02:46:13.036110+00:00"}