{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NWDGEURFAIWGUONV6EQWAXRLVC","short_pith_number":"pith:NWDGEURF","schema_version":"1.0","canonical_sha256":"6d86625225022c6a39b5f121605e2ba8af00b3601b11faaee800bfb4a4e4b418","source":{"kind":"arxiv","id":"2405.01293","version":1},"attestation_state":"computed","paper":{"title":"Low-resource speech recognition and dialect identification of Irish in a multi-task framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ailbhe N\\'i Chasaide, Christer Gobl, Liam Lonergan, Mengjie Qian, Neasa N\\'i Chiar\\'ain","submitted_at":"2024-05-02T13:54:39Z","abstract_excerpt":"This paper explores the use of Hybrid CTC/Attention encoder-decoder models trained with Intermediate CTC (InterCTC) for Irish (Gaelic) low-resource speech recognition (ASR) and dialect identification (DID). Results are compared to the current best performing models trained for ASR (TDNN-HMM) and DID (ECAPA-TDNN). An optimal InterCTC setting is initially established using a Conformer encoder. This setting is then used to train a model with an E-branchformer encoder and the performance of both architectures are compared. A multi-task fine-tuning approach is adopted for language model (LM) shallo"},"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":"2405.01293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T13:54:39Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"b6cfd910e5c5380f4bc3b05cf1818e0aa6ba2ac173aa0f3025eb1ce5fec56c25","abstract_canon_sha256":"09480f65754f0a573d216e6de756dbef742154b4d6e662212d66baf9587801e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:43.481379Z","signature_b64":"QEtXIwjAj/3INZAoOD8LRe3r96h17VGvch9ltjVpyJw1a/gMEgh77tIW8rQLexNY3ntvE4WX38TrRuYEbLERCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d86625225022c6a39b5f121605e2ba8af00b3601b11faaee800bfb4a4e4b418","last_reissued_at":"2026-07-05T08:14:43.480901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:43.480901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-resource speech recognition and dialect identification of Irish in a multi-task framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ailbhe N\\'i Chasaide, Christer Gobl, Liam Lonergan, Mengjie Qian, Neasa N\\'i Chiar\\'ain","submitted_at":"2024-05-02T13:54:39Z","abstract_excerpt":"This paper explores the use of Hybrid CTC/Attention encoder-decoder models trained with Intermediate CTC (InterCTC) for Irish (Gaelic) low-resource speech recognition (ASR) and dialect identification (DID). Results are compared to the current best performing models trained for ASR (TDNN-HMM) and DID (ECAPA-TDNN). An optimal InterCTC setting is initially established using a Conformer encoder. This setting is then used to train a model with an E-branchformer encoder and the performance of both architectures are compared. A multi-task fine-tuning approach is adopted for language model (LM) shallo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01293","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/2405.01293/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":"2405.01293","created_at":"2026-07-05T08:14:43.480981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.01293v1","created_at":"2026-07-05T08:14:43.480981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01293","created_at":"2026-07-05T08:14:43.480981+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWDGEURFAIWG","created_at":"2026-07-05T08:14:43.480981+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWDGEURFAIWGUONV","created_at":"2026-07-05T08:14:43.480981+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWDGEURF","created_at":"2026-07-05T08:14:43.480981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10736","citing_title":"BlasBench: An Open Benchmark for Irish Speech Recognition","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWDGEURFAIWGUONV6EQWAXRLVC","json":"https://pith.science/pith/NWDGEURFAIWGUONV6EQWAXRLVC.json","graph_json":"https://pith.science/api/pith-number/NWDGEURFAIWGUONV6EQWAXRLVC/graph.json","events_json":"https://pith.science/api/pith-number/NWDGEURFAIWGUONV6EQWAXRLVC/events.json","paper":"https://pith.science/paper/NWDGEURF"},"agent_actions":{"view_html":"https://pith.science/pith/NWDGEURFAIWGUONV6EQWAXRLVC","download_json":"https://pith.science/pith/NWDGEURFAIWGUONV6EQWAXRLVC.json","view_paper":"https://pith.science/paper/NWDGEURF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.01293&json=true","fetch_graph":"https://pith.science/api/pith-number/NWDGEURFAIWGUONV6EQWAXRLVC/graph.json","fetch_events":"https://pith.science/api/pith-number/NWDGEURFAIWGUONV6EQWAXRLVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWDGEURFAIWGUONV6EQWAXRLVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWDGEURFAIWGUONV6EQWAXRLVC/action/storage_attestation","attest_author":"https://pith.science/pith/NWDGEURFAIWGUONV6EQWAXRLVC/action/author_attestation","sign_citation":"https://pith.science/pith/NWDGEURFAIWGUONV6EQWAXRLVC/action/citation_signature","submit_replication":"https://pith.science/pith/NWDGEURFAIWGUONV6EQWAXRLVC/action/replication_record"}},"created_at":"2026-07-05T08:14:43.480981+00:00","updated_at":"2026-07-05T08:14:43.480981+00:00"}