{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XKZJMHKYHNOU63LAWCESOYIRQN","short_pith_number":"pith:XKZJMHKY","schema_version":"1.0","canonical_sha256":"bab2961d583b5d4f6d60b089276111836e85579e88bb1a3559a1147d2d8ef7b7","source":{"kind":"arxiv","id":"2309.11585","version":2},"attestation_state":"computed","paper":{"title":"SpeechAlign: a Framework for Speech Translation Alignment Evaluation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleix Sant, Belen Alastruey, David Dale, Gerard I. G\\'allego, Marta R. Costa-juss\\`a","submitted_at":"2023-09-20T18:46:37Z","abstract_excerpt":"Speech-to-Speech and Speech-to-Text translation are currently dynamic areas of research. In our commitment to advance these fields, we present SpeechAlign, a framework designed to evaluate the underexplored field of source-target alignment in speech models. The SpeechAlign framework has two core components. First, to tackle the absence of suitable evaluation datasets, we introduce the Speech Gold Alignment dataset, built upon a English-German text translation gold alignment dataset. Secondly, we introduce two novel metrics, Speech Alignment Error Rate (SAER) and Time-weighted Speech Alignment "},"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":"2309.11585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T18:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"e9f10fc6c8fdee2818b14417d4229d8b5969304a3f450d1d9d52c31414113ed1","abstract_canon_sha256":"73118ae7ce6ba43a7ff3ac19ab3dc0c6a710730eb15521908273228b78eebf8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:54.479505Z","signature_b64":"EBQZRcX6nEF03vL3rfRUmTJ7G4oJPxvlqWN7MZlnBmoNXrmbkzBXHW2spcheiCs9SQ/++NCYIcbodaLbZ32LAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bab2961d583b5d4f6d60b089276111836e85579e88bb1a3559a1147d2d8ef7b7","last_reissued_at":"2026-07-05T08:11:54.479069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:54.479069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechAlign: a Framework for Speech Translation Alignment Evaluation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleix Sant, Belen Alastruey, David Dale, Gerard I. G\\'allego, Marta R. Costa-juss\\`a","submitted_at":"2023-09-20T18:46:37Z","abstract_excerpt":"Speech-to-Speech and Speech-to-Text translation are currently dynamic areas of research. In our commitment to advance these fields, we present SpeechAlign, a framework designed to evaluate the underexplored field of source-target alignment in speech models. The SpeechAlign framework has two core components. First, to tackle the absence of suitable evaluation datasets, we introduce the Speech Gold Alignment dataset, built upon a English-German text translation gold alignment dataset. Secondly, we introduce two novel metrics, Speech Alignment Error Rate (SAER) and Time-weighted Speech Alignment "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11585","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/2309.11585/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":"2309.11585","created_at":"2026-07-05T08:11:54.479125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11585v2","created_at":"2026-07-05T08:11:54.479125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11585","created_at":"2026-07-05T08:11:54.479125+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKZJMHKYHNOU","created_at":"2026-07-05T08:11:54.479125+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKZJMHKYHNOU63LA","created_at":"2026-07-05T08:11:54.479125+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKZJMHKY","created_at":"2026-07-05T08:11:54.479125+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/XKZJMHKYHNOU63LAWCESOYIRQN","json":"https://pith.science/pith/XKZJMHKYHNOU63LAWCESOYIRQN.json","graph_json":"https://pith.science/api/pith-number/XKZJMHKYHNOU63LAWCESOYIRQN/graph.json","events_json":"https://pith.science/api/pith-number/XKZJMHKYHNOU63LAWCESOYIRQN/events.json","paper":"https://pith.science/paper/XKZJMHKY"},"agent_actions":{"view_html":"https://pith.science/pith/XKZJMHKYHNOU63LAWCESOYIRQN","download_json":"https://pith.science/pith/XKZJMHKYHNOU63LAWCESOYIRQN.json","view_paper":"https://pith.science/paper/XKZJMHKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11585&json=true","fetch_graph":"https://pith.science/api/pith-number/XKZJMHKYHNOU63LAWCESOYIRQN/graph.json","fetch_events":"https://pith.science/api/pith-number/XKZJMHKYHNOU63LAWCESOYIRQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKZJMHKYHNOU63LAWCESOYIRQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKZJMHKYHNOU63LAWCESOYIRQN/action/storage_attestation","attest_author":"https://pith.science/pith/XKZJMHKYHNOU63LAWCESOYIRQN/action/author_attestation","sign_citation":"https://pith.science/pith/XKZJMHKYHNOU63LAWCESOYIRQN/action/citation_signature","submit_replication":"https://pith.science/pith/XKZJMHKYHNOU63LAWCESOYIRQN/action/replication_record"}},"created_at":"2026-07-05T08:11:54.479125+00:00","updated_at":"2026-07-05T08:11:54.479125+00:00"}