{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:O5YOIV4XT3Y3GJ34WHIUJXRWBD","short_pith_number":"pith:O5YOIV4X","schema_version":"1.0","canonical_sha256":"7770e457979ef1b3277cb1d144de3608d89abbfe43140244567d49e4f626458e","source":{"kind":"arxiv","id":"1709.01703","version":2},"attestation_state":"computed","paper":{"title":"Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP","stat.ML"],"primary_cat":"eess.AS","authors_text":"Daniel Michelsanti, Zheng-Hua Tan","submitted_at":"2017-09-06T07:51:18Z","abstract_excerpt":"Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks (GANs) in a variety of image processing tasks, we explore the potential of conditional GANs (cGANs) for SE, and in particular, we make use of the image processing framework proposed by Isola et al. [1] to learn a mapping from the spectrogram of noisy speech to an enhanced counterpart. The SE cGAN consists of two networks, trained in an adversarial manner: a"},"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":"1709.01703","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2017-09-06T07:51:18Z","cross_cats_sorted":["cs.LG","cs.SD","eess.SP","stat.ML"],"title_canon_sha256":"9ff0c901881cc7b3e1b1fc16ce173d586d60038297f91b03028b1788749acda3","abstract_canon_sha256":"3c94990e2a8fe98619ee9d5448af3a9b86a0652dc0eddb1771fc2e7704625979"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:29.575940Z","signature_b64":"Z8Wcvx77Bn9pjfsggE8rr8kLTgW79/UhwEF6EgPWKyvvOJ1gCiSIKqoNkRC1nNcRhAfMWYxgtKDS0Y6BgHutBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7770e457979ef1b3277cb1d144de3608d89abbfe43140244567d49e4f626458e","last_reissued_at":"2026-07-05T00:16:29.575524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:29.575524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP","stat.ML"],"primary_cat":"eess.AS","authors_text":"Daniel Michelsanti, Zheng-Hua Tan","submitted_at":"2017-09-06T07:51:18Z","abstract_excerpt":"Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks (GANs) in a variety of image processing tasks, we explore the potential of conditional GANs (cGANs) for SE, and in particular, we make use of the image processing framework proposed by Isola et al. [1] to learn a mapping from the spectrogram of noisy speech to an enhanced counterpart. The SE cGAN consists of two networks, trained in an adversarial manner: a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01703","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/1709.01703/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":"1709.01703","created_at":"2026-07-05T00:16:29.575577+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.01703v2","created_at":"2026-07-05T00:16:29.575577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01703","created_at":"2026-07-05T00:16:29.575577+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5YOIV4XT3Y3","created_at":"2026-07-05T00:16:29.575577+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5YOIV4XT3Y3GJ34","created_at":"2026-07-05T00:16:29.575577+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5YOIV4X","created_at":"2026-07-05T00:16:29.575577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08306","citing_title":"Evaluating the Impact of Discriminative and Generative E2E Speech Enhancement Models on Syllable Stress Preservation","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O5YOIV4XT3Y3GJ34WHIUJXRWBD","json":"https://pith.science/pith/O5YOIV4XT3Y3GJ34WHIUJXRWBD.json","graph_json":"https://pith.science/api/pith-number/O5YOIV4XT3Y3GJ34WHIUJXRWBD/graph.json","events_json":"https://pith.science/api/pith-number/O5YOIV4XT3Y3GJ34WHIUJXRWBD/events.json","paper":"https://pith.science/paper/O5YOIV4X"},"agent_actions":{"view_html":"https://pith.science/pith/O5YOIV4XT3Y3GJ34WHIUJXRWBD","download_json":"https://pith.science/pith/O5YOIV4XT3Y3GJ34WHIUJXRWBD.json","view_paper":"https://pith.science/paper/O5YOIV4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.01703&json=true","fetch_graph":"https://pith.science/api/pith-number/O5YOIV4XT3Y3GJ34WHIUJXRWBD/graph.json","fetch_events":"https://pith.science/api/pith-number/O5YOIV4XT3Y3GJ34WHIUJXRWBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5YOIV4XT3Y3GJ34WHIUJXRWBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5YOIV4XT3Y3GJ34WHIUJXRWBD/action/storage_attestation","attest_author":"https://pith.science/pith/O5YOIV4XT3Y3GJ34WHIUJXRWBD/action/author_attestation","sign_citation":"https://pith.science/pith/O5YOIV4XT3Y3GJ34WHIUJXRWBD/action/citation_signature","submit_replication":"https://pith.science/pith/O5YOIV4XT3Y3GJ34WHIUJXRWBD/action/replication_record"}},"created_at":"2026-07-05T00:16:29.575577+00:00","updated_at":"2026-07-05T00:16:29.575577+00:00"}