{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6XYQEP6ZIRXV6I4XOXVPOHBDUX","short_pith_number":"pith:6XYQEP6Z","schema_version":"1.0","canonical_sha256":"f5f1023fd9446f5f239775eaf71c23a5fde4d0d949b2c4c46dc49ea11d81f802","source":{"kind":"arxiv","id":"1804.00732","version":3},"attestation_state":"computed","paper":{"title":"Speaker-Invariant Training via Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Biing-Hwang (Fred) Juang, Jinyu Li, Vadim Mazalov, Yifan Gong, Yong Zhao, Zhong Meng, Zhuo Chen","submitted_at":"2018-04-02T21:09:30Z","abstract_excerpt":"We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based ASR system. We call the scheme speaker-invariant training (SIT). In SIT, a DNN acoustic model and a speaker classifier network are jointly optimized to minimize the senone (tied triphone state) classification loss, and simultaneously mini-maximize the speaker classification loss. A speaker-invariant and senone-discriminative deep feature is learned through "},"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":"1804.00732","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-04-02T21:09:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"1701e5f34a4a1d19e5316367f7c0e907d587182f0ca850777e8fbb8411a06ecb","abstract_canon_sha256":"56ccf2f0f4588328e7e6671d92371319c80ea840e85139fc1853ba3208b59399"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:31.284700Z","signature_b64":"dCq/N7nPB+0si8fZCl49w4puhKe5slUd+wo4rFWKg2viGwQG/le7f9yTw9XUriRd4oQBSsMzfKDD/XIAsZoCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5f1023fd9446f5f239775eaf71c23a5fde4d0d949b2c4c46dc49ea11d81f802","last_reissued_at":"2026-05-17T23:47:31.284010Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:31.284010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker-Invariant Training via Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Biing-Hwang (Fred) Juang, Jinyu Li, Vadim Mazalov, Yifan Gong, Yong Zhao, Zhong Meng, Zhuo Chen","submitted_at":"2018-04-02T21:09:30Z","abstract_excerpt":"We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based ASR system. We call the scheme speaker-invariant training (SIT). In SIT, a DNN acoustic model and a speaker classifier network are jointly optimized to minimize the senone (tied triphone state) classification loss, and simultaneously mini-maximize the speaker classification loss. A speaker-invariant and senone-discriminative deep feature is learned through "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00732","kind":"arxiv","version":3},"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":"1804.00732","created_at":"2026-05-17T23:47:31.284123+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.00732v3","created_at":"2026-05-17T23:47:31.284123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00732","created_at":"2026-05-17T23:47:31.284123+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XYQEP6ZIRXV","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XYQEP6ZIRXV6I4X","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XYQEP6Z","created_at":"2026-05-18T12:32:11.075285+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/6XYQEP6ZIRXV6I4XOXVPOHBDUX","json":"https://pith.science/pith/6XYQEP6ZIRXV6I4XOXVPOHBDUX.json","graph_json":"https://pith.science/api/pith-number/6XYQEP6ZIRXV6I4XOXVPOHBDUX/graph.json","events_json":"https://pith.science/api/pith-number/6XYQEP6ZIRXV6I4XOXVPOHBDUX/events.json","paper":"https://pith.science/paper/6XYQEP6Z"},"agent_actions":{"view_html":"https://pith.science/pith/6XYQEP6ZIRXV6I4XOXVPOHBDUX","download_json":"https://pith.science/pith/6XYQEP6ZIRXV6I4XOXVPOHBDUX.json","view_paper":"https://pith.science/paper/6XYQEP6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.00732&json=true","fetch_graph":"https://pith.science/api/pith-number/6XYQEP6ZIRXV6I4XOXVPOHBDUX/graph.json","fetch_events":"https://pith.science/api/pith-number/6XYQEP6ZIRXV6I4XOXVPOHBDUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XYQEP6ZIRXV6I4XOXVPOHBDUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XYQEP6ZIRXV6I4XOXVPOHBDUX/action/storage_attestation","attest_author":"https://pith.science/pith/6XYQEP6ZIRXV6I4XOXVPOHBDUX/action/author_attestation","sign_citation":"https://pith.science/pith/6XYQEP6ZIRXV6I4XOXVPOHBDUX/action/citation_signature","submit_replication":"https://pith.science/pith/6XYQEP6ZIRXV6I4XOXVPOHBDUX/action/replication_record"}},"created_at":"2026-05-17T23:47:31.284123+00:00","updated_at":"2026-05-17T23:47:31.284123+00:00"}