{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DNJWFK3GDCEOMPVWJAVUOCVIWG","short_pith_number":"pith:DNJWFK3G","schema_version":"1.0","canonical_sha256":"1b5362ab661888e63eb6482b470aa8b1a60f6f6928e9bb9fe4fe472f224072da","source":{"kind":"arxiv","id":"2005.10407","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bin Ma, Chongjia Ni, Eng Siong Chng, Haihua Xu, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2020-05-21T00:56:42Z","abstract_excerpt":"In this work, we study leveraging extra text data to improve low-resource end-to-end ASR under cross-lingual transfer learning setting. To this end, we extend our prior work [1], and propose a hybrid Transformer-LSTM based architecture. This architecture not only takes advantage of the highly effective encoding capacity of the Transformer network but also benefits from extra text data due to the LSTM-based independent language model network. We conduct experiments on our in-house Malay corpus which contains limited labeled data and a large amount of extra text. Results show that the proposed 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":"2005.10407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-21T00:56:42Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"a7aa845f105410ea80074349fb00dc85098e0310156000c870a75460c28ace20","abstract_canon_sha256":"12be98756a8c75e0a14f4c5d321c91a5d5193f0654278b8db5b85344fc7ec57e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:22.219524Z","signature_b64":"ARSR2s+0J+v4l2krtGxYpE8NCHJIyFU72cQaEl3oJN32EKzuP2GHAgyR23SWuFcrPIYynvbbAj7LZhaRvPFtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b5362ab661888e63eb6482b470aa8b1a60f6f6928e9bb9fe4fe472f224072da","last_reissued_at":"2026-07-05T01:06:22.219174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:22.219174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bin Ma, Chongjia Ni, Eng Siong Chng, Haihua Xu, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2020-05-21T00:56:42Z","abstract_excerpt":"In this work, we study leveraging extra text data to improve low-resource end-to-end ASR under cross-lingual transfer learning setting. To this end, we extend our prior work [1], and propose a hybrid Transformer-LSTM based architecture. This architecture not only takes advantage of the highly effective encoding capacity of the Transformer network but also benefits from extra text data due to the LSTM-based independent language model network. We conduct experiments on our in-house Malay corpus which contains limited labeled data and a large amount of extra text. Results show that the proposed a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10407","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/2005.10407/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":"2005.10407","created_at":"2026-07-05T01:06:22.219230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.10407v2","created_at":"2026-07-05T01:06:22.219230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10407","created_at":"2026-07-05T01:06:22.219230+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNJWFK3GDCEO","created_at":"2026-07-05T01:06:22.219230+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNJWFK3GDCEOMPVW","created_at":"2026-07-05T01:06:22.219230+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNJWFK3G","created_at":"2026-07-05T01:06:22.219230+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/DNJWFK3GDCEOMPVWJAVUOCVIWG","json":"https://pith.science/pith/DNJWFK3GDCEOMPVWJAVUOCVIWG.json","graph_json":"https://pith.science/api/pith-number/DNJWFK3GDCEOMPVWJAVUOCVIWG/graph.json","events_json":"https://pith.science/api/pith-number/DNJWFK3GDCEOMPVWJAVUOCVIWG/events.json","paper":"https://pith.science/paper/DNJWFK3G"},"agent_actions":{"view_html":"https://pith.science/pith/DNJWFK3GDCEOMPVWJAVUOCVIWG","download_json":"https://pith.science/pith/DNJWFK3GDCEOMPVWJAVUOCVIWG.json","view_paper":"https://pith.science/paper/DNJWFK3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.10407&json=true","fetch_graph":"https://pith.science/api/pith-number/DNJWFK3GDCEOMPVWJAVUOCVIWG/graph.json","fetch_events":"https://pith.science/api/pith-number/DNJWFK3GDCEOMPVWJAVUOCVIWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNJWFK3GDCEOMPVWJAVUOCVIWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNJWFK3GDCEOMPVWJAVUOCVIWG/action/storage_attestation","attest_author":"https://pith.science/pith/DNJWFK3GDCEOMPVWJAVUOCVIWG/action/author_attestation","sign_citation":"https://pith.science/pith/DNJWFK3GDCEOMPVWJAVUOCVIWG/action/citation_signature","submit_replication":"https://pith.science/pith/DNJWFK3GDCEOMPVWJAVUOCVIWG/action/replication_record"}},"created_at":"2026-07-05T01:06:22.219230+00:00","updated_at":"2026-07-05T01:06:22.219230+00:00"}