{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R7UVP7AU5XCSUTNVG3TXQRSCHW","short_pith_number":"pith:R7UVP7AU","schema_version":"1.0","canonical_sha256":"8fe957fc14edc52a4db536e77846423d93005afb9a2982e460e8a0f0646d7fc0","source":{"kind":"arxiv","id":"2606.31947","version":1},"attestation_state":"computed","paper":{"title":"LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nina Hosseini-Kivanani, Sandipana Dowerah","submitted_at":"2026-06-30T16:53:15Z","abstract_excerpt":"State-of-the-art speech datasets predominantly focus on widely spoken languages, often overlooking low-resource languages such as Luxembourgish, which remain underrepresented in speech technology research. In this work, we introduce LuxEmo, a 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories. LuxEmo is derived from Radio T\\'el\\'evision Luxembourg (RTL) youth broadcasts, using automated detection followed by human validation. We propose a semi-automatic curation workflow combining voice activity detection, denoising, language identification, LuxASR-base"},"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":"2606.31947","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T16:53:15Z","cross_cats_sorted":[],"title_canon_sha256":"497d6a3b2684a008a235122dc6d0f028dba7b71c70a14126bd7c2b731ae0c70b","abstract_canon_sha256":"774f2caad5927d4c012d4941a7a05dec6636f0f91c72b590a2cf682bd12e838a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:26.743630Z","signature_b64":"dbCK/hKrEjOtdIL987i9X858pWwXifo4X5pqiwYM0OewIuM3ueOZ7SEK5ZYSeEn6aD48zYpR2dllW5c83rQvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fe957fc14edc52a4db536e77846423d93005afb9a2982e460e8a0f0646d7fc0","last_reissued_at":"2026-07-01T01:18:26.743148Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:26.743148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nina Hosseini-Kivanani, Sandipana Dowerah","submitted_at":"2026-06-30T16:53:15Z","abstract_excerpt":"State-of-the-art speech datasets predominantly focus on widely spoken languages, often overlooking low-resource languages such as Luxembourgish, which remain underrepresented in speech technology research. In this work, we introduce LuxEmo, a 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories. LuxEmo is derived from Radio T\\'el\\'evision Luxembourg (RTL) youth broadcasts, using automated detection followed by human validation. We propose a semi-automatic curation workflow combining voice activity detection, denoising, language identification, LuxASR-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31947","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/2606.31947/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":"2606.31947","created_at":"2026-07-01T01:18:26.743209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31947v1","created_at":"2026-07-01T01:18:26.743209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31947","created_at":"2026-07-01T01:18:26.743209+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7UVP7AU5XCS","created_at":"2026-07-01T01:18:26.743209+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7UVP7AU5XCSUTNV","created_at":"2026-07-01T01:18:26.743209+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7UVP7AU","created_at":"2026-07-01T01:18:26.743209+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/R7UVP7AU5XCSUTNVG3TXQRSCHW","json":"https://pith.science/pith/R7UVP7AU5XCSUTNVG3TXQRSCHW.json","graph_json":"https://pith.science/api/pith-number/R7UVP7AU5XCSUTNVG3TXQRSCHW/graph.json","events_json":"https://pith.science/api/pith-number/R7UVP7AU5XCSUTNVG3TXQRSCHW/events.json","paper":"https://pith.science/paper/R7UVP7AU"},"agent_actions":{"view_html":"https://pith.science/pith/R7UVP7AU5XCSUTNVG3TXQRSCHW","download_json":"https://pith.science/pith/R7UVP7AU5XCSUTNVG3TXQRSCHW.json","view_paper":"https://pith.science/paper/R7UVP7AU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31947&json=true","fetch_graph":"https://pith.science/api/pith-number/R7UVP7AU5XCSUTNVG3TXQRSCHW/graph.json","fetch_events":"https://pith.science/api/pith-number/R7UVP7AU5XCSUTNVG3TXQRSCHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7UVP7AU5XCSUTNVG3TXQRSCHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7UVP7AU5XCSUTNVG3TXQRSCHW/action/storage_attestation","attest_author":"https://pith.science/pith/R7UVP7AU5XCSUTNVG3TXQRSCHW/action/author_attestation","sign_citation":"https://pith.science/pith/R7UVP7AU5XCSUTNVG3TXQRSCHW/action/citation_signature","submit_replication":"https://pith.science/pith/R7UVP7AU5XCSUTNVG3TXQRSCHW/action/replication_record"}},"created_at":"2026-07-01T01:18:26.743209+00:00","updated_at":"2026-07-01T01:18:26.743209+00:00"}