{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GSECKRL4MMRWSIF5AVFL5EIX6D","short_pith_number":"pith:GSECKRL4","schema_version":"1.0","canonical_sha256":"348825457c63236920bd054abe9117f0cb510bf1d1aa3aa22a9751a4b490e791","source":{"kind":"arxiv","id":"1711.08010","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jinyu Li, Vadim Mazalov, Yifan Gong, Zhong Meng, Zhuo Chen","submitted_at":"2017-11-21T19:44:37Z","abstract_excerpt":"Unsupervised domain adaptation of speech signal aims at adapting a well-trained source-domain acoustic model to the unlabeled data from target domain. This can be achieved by adversarial training of deep neural network (DNN) acoustic models to learn an intermediate deep representation that is both senone-discriminative and domain-invariant. Specifically, the DNN is trained to jointly optimize the primary task of senone classification and the secondary task of domain classification with adversarial objective functions. In this work, instead of only focusing on learning a domain-invariant featur"},"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":"1711.08010","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-21T19:44:37Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"ae1a2a3320e4fd52e601df0e60bd34258a894da4dc28c7ad876313d98e77f4c1","abstract_canon_sha256":"e093b04f40b9413f7c8697a1b6cd864fe5a114cb7467e5b6f1892bfba43c3525"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:31.718741Z","signature_b64":"WbKS/B5NhkEE29e5cBi7R72VhH9w8BLkjRNS3pcYj5fJn9MvFiTT8eTpnYwf8RxYTNho8orgUmnyWrXiRAJECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"348825457c63236920bd054abe9117f0cb510bf1d1aa3aa22a9751a4b490e791","last_reissued_at":"2026-05-17T23:47:31.718049Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:31.718049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jinyu Li, Vadim Mazalov, Yifan Gong, Zhong Meng, Zhuo Chen","submitted_at":"2017-11-21T19:44:37Z","abstract_excerpt":"Unsupervised domain adaptation of speech signal aims at adapting a well-trained source-domain acoustic model to the unlabeled data from target domain. This can be achieved by adversarial training of deep neural network (DNN) acoustic models to learn an intermediate deep representation that is both senone-discriminative and domain-invariant. Specifically, the DNN is trained to jointly optimize the primary task of senone classification and the secondary task of domain classification with adversarial objective functions. In this work, instead of only focusing on learning a domain-invariant featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08010","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":"1711.08010","created_at":"2026-05-17T23:47:31.718162+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08010v2","created_at":"2026-05-17T23:47:31.718162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08010","created_at":"2026-05-17T23:47:31.718162+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSECKRL4MMRW","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSECKRL4MMRWSIF5","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSECKRL4","created_at":"2026-05-18T12:31:18.294218+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/GSECKRL4MMRWSIF5AVFL5EIX6D","json":"https://pith.science/pith/GSECKRL4MMRWSIF5AVFL5EIX6D.json","graph_json":"https://pith.science/api/pith-number/GSECKRL4MMRWSIF5AVFL5EIX6D/graph.json","events_json":"https://pith.science/api/pith-number/GSECKRL4MMRWSIF5AVFL5EIX6D/events.json","paper":"https://pith.science/paper/GSECKRL4"},"agent_actions":{"view_html":"https://pith.science/pith/GSECKRL4MMRWSIF5AVFL5EIX6D","download_json":"https://pith.science/pith/GSECKRL4MMRWSIF5AVFL5EIX6D.json","view_paper":"https://pith.science/paper/GSECKRL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08010&json=true","fetch_graph":"https://pith.science/api/pith-number/GSECKRL4MMRWSIF5AVFL5EIX6D/graph.json","fetch_events":"https://pith.science/api/pith-number/GSECKRL4MMRWSIF5AVFL5EIX6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSECKRL4MMRWSIF5AVFL5EIX6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSECKRL4MMRWSIF5AVFL5EIX6D/action/storage_attestation","attest_author":"https://pith.science/pith/GSECKRL4MMRWSIF5AVFL5EIX6D/action/author_attestation","sign_citation":"https://pith.science/pith/GSECKRL4MMRWSIF5AVFL5EIX6D/action/citation_signature","submit_replication":"https://pith.science/pith/GSECKRL4MMRWSIF5AVFL5EIX6D/action/replication_record"}},"created_at":"2026-05-17T23:47:31.718162+00:00","updated_at":"2026-05-17T23:47:31.718162+00:00"}