{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IWA2FY4XV32GE236JJVYAHCPPK","short_pith_number":"pith:IWA2FY4X","schema_version":"1.0","canonical_sha256":"4581a2e397aef4626b7e4a6b801c4f7aa0582c0f4bd250d59e78bdaad6a46027","source":{"kind":"arxiv","id":"1802.03142","version":1},"attestation_state":"computed","paper":{"title":"Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Can Kocabiyikoglu, Laurent Besacier, Olivier Kraif","submitted_at":"2018-02-09T06:29:43Z","abstract_excerpt":"Recent works in spoken language translation (SLT) have attempted to build end-to-end speech-to-text translation without using source language transcription during learning or decoding. However, while large quantities of parallel texts (such as Europarl, OpenSubtitles) are available for training machine translation systems, there are no large (100h) and open source parallel corpora that include speech in a source language aligned to text in a target language. This paper tries to fill this gap by augmenting an existing (monolingual) corpus: LibriSpeech. This corpus, used for automatic speech rec"},"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":"1802.03142","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-02-09T06:29:43Z","cross_cats_sorted":[],"title_canon_sha256":"e1eecb49ed642735e8f6f4dad308fcf683bb44f6f5672d6cf6e78d85adf06064","abstract_canon_sha256":"374f1f501f7d9ad38a6188f775a518684f6b883e386ce1b904774d686a0a34f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:58.471597Z","signature_b64":"AuX/KYJOePz0csW1F+3FZIqO/mvzSF4tYC3lH0GV+VXKuhwSFTI2tCvagp/z9nQenKsBv8cwrUlKafi9EqKUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4581a2e397aef4626b7e4a6b801c4f7aa0582c0f4bd250d59e78bdaad6a46027","last_reissued_at":"2026-05-18T00:23:58.471076Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:58.471076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Can Kocabiyikoglu, Laurent Besacier, Olivier Kraif","submitted_at":"2018-02-09T06:29:43Z","abstract_excerpt":"Recent works in spoken language translation (SLT) have attempted to build end-to-end speech-to-text translation without using source language transcription during learning or decoding. However, while large quantities of parallel texts (such as Europarl, OpenSubtitles) are available for training machine translation systems, there are no large (100h) and open source parallel corpora that include speech in a source language aligned to text in a target language. This paper tries to fill this gap by augmenting an existing (monolingual) corpus: LibriSpeech. This corpus, used for automatic speech rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03142","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":""},"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":"1802.03142","created_at":"2026-05-18T00:23:58.471152+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03142v1","created_at":"2026-05-18T00:23:58.471152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03142","created_at":"2026-05-18T00:23:58.471152+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWA2FY4XV32G","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWA2FY4XV32GE236","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWA2FY4X","created_at":"2026-05-18T12:32:31.084164+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/IWA2FY4XV32GE236JJVYAHCPPK","json":"https://pith.science/pith/IWA2FY4XV32GE236JJVYAHCPPK.json","graph_json":"https://pith.science/api/pith-number/IWA2FY4XV32GE236JJVYAHCPPK/graph.json","events_json":"https://pith.science/api/pith-number/IWA2FY4XV32GE236JJVYAHCPPK/events.json","paper":"https://pith.science/paper/IWA2FY4X"},"agent_actions":{"view_html":"https://pith.science/pith/IWA2FY4XV32GE236JJVYAHCPPK","download_json":"https://pith.science/pith/IWA2FY4XV32GE236JJVYAHCPPK.json","view_paper":"https://pith.science/paper/IWA2FY4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03142&json=true","fetch_graph":"https://pith.science/api/pith-number/IWA2FY4XV32GE236JJVYAHCPPK/graph.json","fetch_events":"https://pith.science/api/pith-number/IWA2FY4XV32GE236JJVYAHCPPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWA2FY4XV32GE236JJVYAHCPPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWA2FY4XV32GE236JJVYAHCPPK/action/storage_attestation","attest_author":"https://pith.science/pith/IWA2FY4XV32GE236JJVYAHCPPK/action/author_attestation","sign_citation":"https://pith.science/pith/IWA2FY4XV32GE236JJVYAHCPPK/action/citation_signature","submit_replication":"https://pith.science/pith/IWA2FY4XV32GE236JJVYAHCPPK/action/replication_record"}},"created_at":"2026-05-18T00:23:58.471152+00:00","updated_at":"2026-05-18T00:23:58.471152+00:00"}