{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TAD2IZGFM5EEGIRGTHT43BIGTO","short_pith_number":"pith:TAD2IZGF","schema_version":"1.0","canonical_sha256":"9807a464c5674843222699e7cd85069bb143032bc30de457fb1fde11026635f4","source":{"kind":"arxiv","id":"1810.03459","version":1},"attestation_state":"computed","paper":{"title":"Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jaejin Cho, Martin Karafiat, Matthew Wiesner, Murali Karthick Baskar, Nelson Yalta, Ruizhi Li, Shinji Watanabe, Sri Harish Mallidi, Takaaki Hori","submitted_at":"2018-10-04T08:53:42Z","abstract_excerpt":"Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new direction in speech research. The approach benefits by performing model training without using lexicon and alignments. However, this poses a new problem of requiring more data compared to conventional DNN-HMM systems. In this work, we attempt to use data from 10 BABEL languages to build a multi-lingual seq2seq model as a prior model, and then port them towards 4 other BABEL languages using transfer learning approach. We also explore different architectures for improving the prior multilingual seq2seq model. The pa"},"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":"1810.03459","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-04T08:53:42Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"413264085f41a4deb2e2750a7da316d3b7419a12b0e3052bc301d74c4535b91e","abstract_canon_sha256":"229d6f105a136058926a5ce1267cdb571d592cd1717cdf34c9a6e33c7edf2a75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:51.222999Z","signature_b64":"Q7Hzsb7iACyo4FoKMoTkaK4mfclQhrWP2zghPcD3/8/GDWCU/40NCMA6eVMzvFMg93sAXS6X6TyA7Aa+GR+vCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9807a464c5674843222699e7cd85069bb143032bc30de457fb1fde11026635f4","last_reissued_at":"2026-05-18T00:03:51.222413Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:51.222413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jaejin Cho, Martin Karafiat, Matthew Wiesner, Murali Karthick Baskar, Nelson Yalta, Ruizhi Li, Shinji Watanabe, Sri Harish Mallidi, Takaaki Hori","submitted_at":"2018-10-04T08:53:42Z","abstract_excerpt":"Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new direction in speech research. The approach benefits by performing model training without using lexicon and alignments. However, this poses a new problem of requiring more data compared to conventional DNN-HMM systems. In this work, we attempt to use data from 10 BABEL languages to build a multi-lingual seq2seq model as a prior model, and then port them towards 4 other BABEL languages using transfer learning approach. We also explore different architectures for improving the prior multilingual seq2seq model. The pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03459","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":"1810.03459","created_at":"2026-05-18T00:03:51.222500+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03459v1","created_at":"2026-05-18T00:03:51.222500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03459","created_at":"2026-05-18T00:03:51.222500+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAD2IZGFM5EE","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAD2IZGFM5EEGIRG","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAD2IZGF","created_at":"2026-05-18T12:32:53.628368+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/TAD2IZGFM5EEGIRGTHT43BIGTO","json":"https://pith.science/pith/TAD2IZGFM5EEGIRGTHT43BIGTO.json","graph_json":"https://pith.science/api/pith-number/TAD2IZGFM5EEGIRGTHT43BIGTO/graph.json","events_json":"https://pith.science/api/pith-number/TAD2IZGFM5EEGIRGTHT43BIGTO/events.json","paper":"https://pith.science/paper/TAD2IZGF"},"agent_actions":{"view_html":"https://pith.science/pith/TAD2IZGFM5EEGIRGTHT43BIGTO","download_json":"https://pith.science/pith/TAD2IZGFM5EEGIRGTHT43BIGTO.json","view_paper":"https://pith.science/paper/TAD2IZGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03459&json=true","fetch_graph":"https://pith.science/api/pith-number/TAD2IZGFM5EEGIRGTHT43BIGTO/graph.json","fetch_events":"https://pith.science/api/pith-number/TAD2IZGFM5EEGIRGTHT43BIGTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAD2IZGFM5EEGIRGTHT43BIGTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAD2IZGFM5EEGIRGTHT43BIGTO/action/storage_attestation","attest_author":"https://pith.science/pith/TAD2IZGFM5EEGIRGTHT43BIGTO/action/author_attestation","sign_citation":"https://pith.science/pith/TAD2IZGFM5EEGIRGTHT43BIGTO/action/citation_signature","submit_replication":"https://pith.science/pith/TAD2IZGFM5EEGIRGTHT43BIGTO/action/replication_record"}},"created_at":"2026-05-18T00:03:51.222500+00:00","updated_at":"2026-05-18T00:03:51.222500+00:00"}