{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PMZ46TPYKCDRU5RRFOH33A5WU5","short_pith_number":"pith:PMZ46TPY","schema_version":"1.0","canonical_sha256":"7b33cf4df850871a76312b8fbd83b6a75cc3bf6d5bcc6413289459d93b5a15c5","source":{"kind":"arxiv","id":"1911.11935","version":1},"attestation_state":"computed","paper":{"title":"AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ching-Feng Yeh, Mahaveer Jain, Michael L. Seltzer, Yi-Chen Chen, Zhaojun Yang","submitted_at":"2019-11-27T03:42:21Z","abstract_excerpt":"As one of the major sources in speech variability, accents have posed a grand challenge to the robustness of speech recognition systems. In this paper, our goal is to build a unified end-to-end speech recognition system that generalizes well across accents. For this purpose, we propose a novel pre-training framework AIPNet based on generative adversarial nets (GAN) for accent-invariant representation learning: Accent Invariant Pre-training Networks. We pre-train AIPNet to disentangle accent-invariant and accent-specific characteristics from acoustic features through adversarial training on acc"},"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":"1911.11935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-27T03:42:21Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"880aedc7f75ebfd6f2a8c6222e1037da87743735c4e8892393fd14c48ac984f1","abstract_canon_sha256":"28e85a5782336019b1f8ef48b16e71c8e7f759a79ba3f0f65231e9827038a8bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:28.899746Z","signature_b64":"gJH8oFl4lX9IzjWlCmF6aoVgASJA8hfphIZd7RY/DBU5yWHw5lKd721aXNRwxPb1XRpytbFo+FZ5DbKXdRKvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b33cf4df850871a76312b8fbd83b6a75cc3bf6d5bcc6413289459d93b5a15c5","last_reissued_at":"2026-07-05T00:22:28.899255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:28.899255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ching-Feng Yeh, Mahaveer Jain, Michael L. Seltzer, Yi-Chen Chen, Zhaojun Yang","submitted_at":"2019-11-27T03:42:21Z","abstract_excerpt":"As one of the major sources in speech variability, accents have posed a grand challenge to the robustness of speech recognition systems. In this paper, our goal is to build a unified end-to-end speech recognition system that generalizes well across accents. For this purpose, we propose a novel pre-training framework AIPNet based on generative adversarial nets (GAN) for accent-invariant representation learning: Accent Invariant Pre-training Networks. We pre-train AIPNet to disentangle accent-invariant and accent-specific characteristics from acoustic features through adversarial training on acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11935","kind":"arxiv","version":1},"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/1911.11935/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":"1911.11935","created_at":"2026-07-05T00:22:28.899319+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.11935v1","created_at":"2026-07-05T00:22:28.899319+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11935","created_at":"2026-07-05T00:22:28.899319+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMZ46TPYKCDR","created_at":"2026-07-05T00:22:28.899319+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMZ46TPYKCDRU5RR","created_at":"2026-07-05T00:22:28.899319+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMZ46TPY","created_at":"2026-07-05T00:22:28.899319+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/PMZ46TPYKCDRU5RRFOH33A5WU5","json":"https://pith.science/pith/PMZ46TPYKCDRU5RRFOH33A5WU5.json","graph_json":"https://pith.science/api/pith-number/PMZ46TPYKCDRU5RRFOH33A5WU5/graph.json","events_json":"https://pith.science/api/pith-number/PMZ46TPYKCDRU5RRFOH33A5WU5/events.json","paper":"https://pith.science/paper/PMZ46TPY"},"agent_actions":{"view_html":"https://pith.science/pith/PMZ46TPYKCDRU5RRFOH33A5WU5","download_json":"https://pith.science/pith/PMZ46TPYKCDRU5RRFOH33A5WU5.json","view_paper":"https://pith.science/paper/PMZ46TPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.11935&json=true","fetch_graph":"https://pith.science/api/pith-number/PMZ46TPYKCDRU5RRFOH33A5WU5/graph.json","fetch_events":"https://pith.science/api/pith-number/PMZ46TPYKCDRU5RRFOH33A5WU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMZ46TPYKCDRU5RRFOH33A5WU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMZ46TPYKCDRU5RRFOH33A5WU5/action/storage_attestation","attest_author":"https://pith.science/pith/PMZ46TPYKCDRU5RRFOH33A5WU5/action/author_attestation","sign_citation":"https://pith.science/pith/PMZ46TPYKCDRU5RRFOH33A5WU5/action/citation_signature","submit_replication":"https://pith.science/pith/PMZ46TPYKCDRU5RRFOH33A5WU5/action/replication_record"}},"created_at":"2026-07-05T00:22:28.899319+00:00","updated_at":"2026-07-05T00:22:28.899319+00:00"}