{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XC7ETD65D27KMKJL62GTXDH4AJ","short_pith_number":"pith:XC7ETD65","schema_version":"1.0","canonical_sha256":"b8be498fdd1ebea6292bf68d3b8cfc027948fca95e50bcf737028636f282cec5","source":{"kind":"arxiv","id":"2108.01280","version":1},"attestation_state":"computed","paper":{"title":"A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Huseyin Atakan Varol, Saida Mussakhojayeva, Yerbolat Khassanov","submitted_at":"2021-08-03T04:04:01Z","abstract_excerpt":"We study training a single end-to-end (E2E) automatic speech recognition (ASR) model for three languages used in Kazakhstan: Kazakh, Russian, and English. We first describe the development of multilingual E2E ASR based on Transformer networks and then perform an extensive assessment on the aforementioned languages. We also compare two variants of output grapheme set construction: combined and independent. Furthermore, we evaluate the impact of LMs and data augmentation techniques on the recognition performance of the multilingual E2E ASR. In addition, we present several datasets for training 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":"2108.01280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-08-03T04:04:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b770f7091f173d393a3b5e06f5787f5406512f831ded265d5a335770ead287a0","abstract_canon_sha256":"8f1cf8dca89c5dc11c07235337395d71d77515effb1b5890cf38f36906392b9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:01.072126Z","signature_b64":"Eo8+kcgNoZqfbr91jienYdfyYeVRNgcwEtY7BC+LR7JB3EEOZaNz0Rp5bp3JPea7Z5giEd5kg5GgYsR5swGBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8be498fdd1ebea6292bf68d3b8cfc027948fca95e50bcf737028636f282cec5","last_reissued_at":"2026-07-05T03:03:01.071665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:01.071665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Huseyin Atakan Varol, Saida Mussakhojayeva, Yerbolat Khassanov","submitted_at":"2021-08-03T04:04:01Z","abstract_excerpt":"We study training a single end-to-end (E2E) automatic speech recognition (ASR) model for three languages used in Kazakhstan: Kazakh, Russian, and English. We first describe the development of multilingual E2E ASR based on Transformer networks and then perform an extensive assessment on the aforementioned languages. We also compare two variants of output grapheme set construction: combined and independent. Furthermore, we evaluate the impact of LMs and data augmentation techniques on the recognition performance of the multilingual E2E ASR. In addition, we present several datasets for training a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01280","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/2108.01280/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":"2108.01280","created_at":"2026-07-05T03:03:01.071729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01280v1","created_at":"2026-07-05T03:03:01.071729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01280","created_at":"2026-07-05T03:03:01.071729+00:00"},{"alias_kind":"pith_short_12","alias_value":"XC7ETD65D27K","created_at":"2026-07-05T03:03:01.071729+00:00"},{"alias_kind":"pith_short_16","alias_value":"XC7ETD65D27KMKJL","created_at":"2026-07-05T03:03:01.071729+00:00"},{"alias_kind":"pith_short_8","alias_value":"XC7ETD65","created_at":"2026-07-05T03:03:01.071729+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/XC7ETD65D27KMKJL62GTXDH4AJ","json":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ.json","graph_json":"https://pith.science/api/pith-number/XC7ETD65D27KMKJL62GTXDH4AJ/graph.json","events_json":"https://pith.science/api/pith-number/XC7ETD65D27KMKJL62GTXDH4AJ/events.json","paper":"https://pith.science/paper/XC7ETD65"},"agent_actions":{"view_html":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ","download_json":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ.json","view_paper":"https://pith.science/paper/XC7ETD65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01280&json=true","fetch_graph":"https://pith.science/api/pith-number/XC7ETD65D27KMKJL62GTXDH4AJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XC7ETD65D27KMKJL62GTXDH4AJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ/action/storage_attestation","attest_author":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ/action/author_attestation","sign_citation":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ/action/citation_signature","submit_replication":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ/action/replication_record"}},"created_at":"2026-07-05T03:03:01.071729+00:00","updated_at":"2026-07-05T03:03:01.071729+00:00"}