{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:4CNHGN25MJJLZI3UICXDTH3FT4","short_pith_number":"pith:4CNHGN25","schema_version":"1.0","canonical_sha256":"e09a73375d6252bca37440ae399f659f0bdd41dd23bc7eddc16a3822df1fa7a0","source":{"kind":"arxiv","id":"1510.08985","version":1},"attestation_state":"computed","paper":{"title":"Prediction-Adaptation-Correction Recurrent Neural Networks for Low-Resource Language Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Ekapol Chuangsuwanich, James Glass, Yu Zhang","submitted_at":"2015-10-30T06:42:03Z","abstract_excerpt":"In this paper, we investigate the use of prediction-adaptation-correction recurrent neural networks (PAC-RNNs) for low-resource speech recognition. A PAC-RNN is comprised of a pair of neural networks in which a {\\it correction} network uses auxiliary information given by a {\\it prediction} network to help estimate the state probability. The information from the correction network is also used by the prediction network in a recurrent loop. Our model outperforms other state-of-the-art neural networks (DNNs, LSTMs) on IARPA-Babel tasks. Moreover, transfer learning from a language that is similar "},"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":"1510.08985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-10-30T06:42:03Z","cross_cats_sorted":["cs.LG","cs.NE","eess.AS"],"title_canon_sha256":"1d6db89159bba69150d863902de7e6cc180f04e2587629830b6b5be8d6a02c7c","abstract_canon_sha256":"f58eb9a2107e45a94b9721a7998877c3bf989a4529ce18fda5cda98eae22b265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:03.979901Z","signature_b64":"FCQLODAJ143HpljVSgnnoMlWxQU9x+lNaqCtJWa+QXLl+/f+nl1xFSq8gTlq0wqcKIfSxMIlC4fEgzBXBmHyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e09a73375d6252bca37440ae399f659f0bdd41dd23bc7eddc16a3822df1fa7a0","last_reissued_at":"2026-05-17T23:59:03.979511Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:03.979511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prediction-Adaptation-Correction Recurrent Neural Networks for Low-Resource Language Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Ekapol Chuangsuwanich, James Glass, Yu Zhang","submitted_at":"2015-10-30T06:42:03Z","abstract_excerpt":"In this paper, we investigate the use of prediction-adaptation-correction recurrent neural networks (PAC-RNNs) for low-resource speech recognition. A PAC-RNN is comprised of a pair of neural networks in which a {\\it correction} network uses auxiliary information given by a {\\it prediction} network to help estimate the state probability. The information from the correction network is also used by the prediction network in a recurrent loop. Our model outperforms other state-of-the-art neural networks (DNNs, LSTMs) on IARPA-Babel tasks. Moreover, transfer learning from a language that is similar "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.08985","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":""},"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":"1510.08985","created_at":"2026-05-17T23:59:03.979573+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.08985v1","created_at":"2026-05-17T23:59:03.979573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.08985","created_at":"2026-05-17T23:59:03.979573+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CNHGN25MJJL","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CNHGN25MJJLZI3U","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CNHGN25","created_at":"2026-05-18T12:29:05.191682+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/4CNHGN25MJJLZI3UICXDTH3FT4","json":"https://pith.science/pith/4CNHGN25MJJLZI3UICXDTH3FT4.json","graph_json":"https://pith.science/api/pith-number/4CNHGN25MJJLZI3UICXDTH3FT4/graph.json","events_json":"https://pith.science/api/pith-number/4CNHGN25MJJLZI3UICXDTH3FT4/events.json","paper":"https://pith.science/paper/4CNHGN25"},"agent_actions":{"view_html":"https://pith.science/pith/4CNHGN25MJJLZI3UICXDTH3FT4","download_json":"https://pith.science/pith/4CNHGN25MJJLZI3UICXDTH3FT4.json","view_paper":"https://pith.science/paper/4CNHGN25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.08985&json=true","fetch_graph":"https://pith.science/api/pith-number/4CNHGN25MJJLZI3UICXDTH3FT4/graph.json","fetch_events":"https://pith.science/api/pith-number/4CNHGN25MJJLZI3UICXDTH3FT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CNHGN25MJJLZI3UICXDTH3FT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CNHGN25MJJLZI3UICXDTH3FT4/action/storage_attestation","attest_author":"https://pith.science/pith/4CNHGN25MJJLZI3UICXDTH3FT4/action/author_attestation","sign_citation":"https://pith.science/pith/4CNHGN25MJJLZI3UICXDTH3FT4/action/citation_signature","submit_replication":"https://pith.science/pith/4CNHGN25MJJLZI3UICXDTH3FT4/action/replication_record"}},"created_at":"2026-05-17T23:59:03.979573+00:00","updated_at":"2026-05-17T23:59:03.979573+00:00"}