{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:PH4JNKXRCB677T5M3YPYYN7SBX","short_pith_number":"pith:PH4JNKXR","schema_version":"1.0","canonical_sha256":"79f896aaf1107dffcfacde1f8c37f20dc0ac2c9995033ea8fd2c264046eac3de","source":{"kind":"arxiv","id":"1612.01744","version":1},"attestation_state":"computed","paper":{"title":"Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Berard, Christophe Servan, Laurent Besacier, Olivier Pietquin","submitted_at":"2016-12-06T10:48:56Z","abstract_excerpt":"This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propose a model for direct speech-to-text translation, which gives promising results on a small French-English synthetic corpus. Relaxing the need for source language transcription would drastically change the data collection methodology in speech translation, especially in under-resourced scenarios. For instance, in the former project DARPA TRANSTAC (speech translation from spoken Arabic dialects), a large effort was dev"},"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":"1612.01744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-12-06T10:48:56Z","cross_cats_sorted":[],"title_canon_sha256":"bba79bc77b914f8fbe4a932c05d354629779dacb2fb2e5333fd4fd890c03d159","abstract_canon_sha256":"422a3a8e9954a7de20b96810e16f58129813ccd3a80ec4ab7e5167e28ce7de14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:47.706780Z","signature_b64":"0htwmp+6YyqS2SARbPgRexG0rEYhL3McO0Au4sDPc7mIcHir2dlmBjegAGEufc7LzuHfvfZS5ajSwVmq2SAOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79f896aaf1107dffcfacde1f8c37f20dc0ac2c9995033ea8fd2c264046eac3de","last_reissued_at":"2026-05-18T00:55:47.706388Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:47.706388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Berard, Christophe Servan, Laurent Besacier, Olivier Pietquin","submitted_at":"2016-12-06T10:48:56Z","abstract_excerpt":"This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propose a model for direct speech-to-text translation, which gives promising results on a small French-English synthetic corpus. Relaxing the need for source language transcription would drastically change the data collection methodology in speech translation, especially in under-resourced scenarios. For instance, in the former project DARPA TRANSTAC (speech translation from spoken Arabic dialects), a large effort was dev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01744","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":"1612.01744","created_at":"2026-05-18T00:55:47.706447+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.01744v1","created_at":"2026-05-18T00:55:47.706447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01744","created_at":"2026-05-18T00:55:47.706447+00:00"},{"alias_kind":"pith_short_12","alias_value":"PH4JNKXRCB67","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"PH4JNKXRCB677T5M","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"PH4JNKXR","created_at":"2026-05-18T12:30:39.010887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.16378","citing_title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PH4JNKXRCB677T5M3YPYYN7SBX","json":"https://pith.science/pith/PH4JNKXRCB677T5M3YPYYN7SBX.json","graph_json":"https://pith.science/api/pith-number/PH4JNKXRCB677T5M3YPYYN7SBX/graph.json","events_json":"https://pith.science/api/pith-number/PH4JNKXRCB677T5M3YPYYN7SBX/events.json","paper":"https://pith.science/paper/PH4JNKXR"},"agent_actions":{"view_html":"https://pith.science/pith/PH4JNKXRCB677T5M3YPYYN7SBX","download_json":"https://pith.science/pith/PH4JNKXRCB677T5M3YPYYN7SBX.json","view_paper":"https://pith.science/paper/PH4JNKXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.01744&json=true","fetch_graph":"https://pith.science/api/pith-number/PH4JNKXRCB677T5M3YPYYN7SBX/graph.json","fetch_events":"https://pith.science/api/pith-number/PH4JNKXRCB677T5M3YPYYN7SBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PH4JNKXRCB677T5M3YPYYN7SBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PH4JNKXRCB677T5M3YPYYN7SBX/action/storage_attestation","attest_author":"https://pith.science/pith/PH4JNKXRCB677T5M3YPYYN7SBX/action/author_attestation","sign_citation":"https://pith.science/pith/PH4JNKXRCB677T5M3YPYYN7SBX/action/citation_signature","submit_replication":"https://pith.science/pith/PH4JNKXRCB677T5M3YPYYN7SBX/action/replication_record"}},"created_at":"2026-05-18T00:55:47.706447+00:00","updated_at":"2026-05-18T00:55:47.706447+00:00"}