{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5IZLIVQUVPSXPIEWCYFRF7MB57","short_pith_number":"pith:5IZLIVQU","schema_version":"1.0","canonical_sha256":"ea32b45614abe577a096160b12fd81efd9af9806f1a7480007f22adcf9349e7a","source":{"kind":"arxiv","id":"2406.17363","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Yasmin Moslem","submitted_at":"2024-06-25T08:26:41Z","abstract_excerpt":"This paper describes our system submission to the International Conference on Spoken Language Translation (IWSLT 2024) for Irish-to-English speech translation. We built end-to-end systems based on Whisper, and employed a number of data augmentation techniques, such as speech back-translation and noise augmentation. We investigate the effect of using synthetic audio data and discuss several methods for enriching signal diversity."},"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":"2406.17363","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T08:26:41Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"27921a7db919780e688e70f4e9f718691d6f2f0fae069a31e018c00a14a2173f","abstract_canon_sha256":"8858f73f77e6942e9547d7b45048b71ac622d21642f702c0dd094dbfe8d7c877"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:21.289029Z","signature_b64":"NtRlIXDfPGrMe63l0ZjJV9ZecILuaj7PobtN0MkC4To6KEIqp3YBcXtXMw0nxJXWQbxgrw+0a4ZXCU0I73LqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea32b45614abe577a096160b12fd81efd9af9806f1a7480007f22adcf9349e7a","last_reissued_at":"2026-07-05T08:37:21.288624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:21.288624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Yasmin Moslem","submitted_at":"2024-06-25T08:26:41Z","abstract_excerpt":"This paper describes our system submission to the International Conference on Spoken Language Translation (IWSLT 2024) for Irish-to-English speech translation. We built end-to-end systems based on Whisper, and employed a number of data augmentation techniques, such as speech back-translation and noise augmentation. We investigate the effect of using synthetic audio data and discuss several methods for enriching signal diversity."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17363","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/2406.17363/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":"2406.17363","created_at":"2026-07-05T08:37:21.288680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17363v2","created_at":"2026-07-05T08:37:21.288680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17363","created_at":"2026-07-05T08:37:21.288680+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IZLIVQUVPSX","created_at":"2026-07-05T08:37:21.288680+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IZLIVQUVPSXPIEW","created_at":"2026-07-05T08:37:21.288680+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IZLIVQU","created_at":"2026-07-05T08:37:21.288680+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":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IZLIVQUVPSXPIEWCYFRF7MB57","json":"https://pith.science/pith/5IZLIVQUVPSXPIEWCYFRF7MB57.json","graph_json":"https://pith.science/api/pith-number/5IZLIVQUVPSXPIEWCYFRF7MB57/graph.json","events_json":"https://pith.science/api/pith-number/5IZLIVQUVPSXPIEWCYFRF7MB57/events.json","paper":"https://pith.science/paper/5IZLIVQU"},"agent_actions":{"view_html":"https://pith.science/pith/5IZLIVQUVPSXPIEWCYFRF7MB57","download_json":"https://pith.science/pith/5IZLIVQUVPSXPIEWCYFRF7MB57.json","view_paper":"https://pith.science/paper/5IZLIVQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17363&json=true","fetch_graph":"https://pith.science/api/pith-number/5IZLIVQUVPSXPIEWCYFRF7MB57/graph.json","fetch_events":"https://pith.science/api/pith-number/5IZLIVQUVPSXPIEWCYFRF7MB57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IZLIVQUVPSXPIEWCYFRF7MB57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IZLIVQUVPSXPIEWCYFRF7MB57/action/storage_attestation","attest_author":"https://pith.science/pith/5IZLIVQUVPSXPIEWCYFRF7MB57/action/author_attestation","sign_citation":"https://pith.science/pith/5IZLIVQUVPSXPIEWCYFRF7MB57/action/citation_signature","submit_replication":"https://pith.science/pith/5IZLIVQUVPSXPIEWCYFRF7MB57/action/replication_record"}},"created_at":"2026-07-05T08:37:21.288680+00:00","updated_at":"2026-07-05T08:37:21.288680+00:00"}