{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ACGMQEIHUJOTZP7WCTXM3A7YQJ","short_pith_number":"pith:ACGMQEIH","schema_version":"1.0","canonical_sha256":"008cc81107a25d3cbff614eecd83f882621fc14eb8dd4dd416085bf48ce701ef","source":{"kind":"arxiv","id":"2605.14766","version":1},"attestation_state":"computed","paper":{"title":"Streaming Speech-to-Text Translation with a SpeechLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Rogier C. van Dalen, Shucong Zhang, Titouan Parcollet, Xianrui Zheng","submitted_at":"2026-05-14T12:32:57Z","abstract_excerpt":"Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those tasks into a SpeechLLM promises to exploit paralinguistic information in the speech and to reduce cascaded errors. But existing SpeechLLM systems are slow since they do not work in a real streaming fashion: they wait for a complete utterance of audio before outputting a translation, or output tokens at fixed intervals, which is not suitable for real applications. This work proposes an LLM-based architecture for real streaming speech-to-text trans"},"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":"2605.14766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T12:32:57Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"23f38ec00b2fa4e1e4cd45e6b706b7f8f05eb55f47b67b5f38527ac119929797","abstract_canon_sha256":"67494c74a8377c1dea644e51463a95ed8e37da493d8a73f48609cd369cbb6cfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:58.701213Z","signature_b64":"xoxpnzboWfPoxtrCg1otS9CAIPJTTBBiXa2F1cak3ypTMecnjUa5feIErZic5hKO9me0GsYr/+/1B69QvoV6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"008cc81107a25d3cbff614eecd83f882621fc14eb8dd4dd416085bf48ce701ef","last_reissued_at":"2026-05-17T23:38:58.700504Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:58.700504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Speech-to-Text Translation with a SpeechLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Rogier C. van Dalen, Shucong Zhang, Titouan Parcollet, Xianrui Zheng","submitted_at":"2026-05-14T12:32:57Z","abstract_excerpt":"Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those tasks into a SpeechLLM promises to exploit paralinguistic information in the speech and to reduce cascaded errors. But existing SpeechLLM systems are slow since they do not work in a real streaming fashion: they wait for a complete utterance of audio before outputting a translation, or output tokens at fixed intervals, which is not suitable for real applications. This work proposes an LLM-based architecture for real streaming speech-to-text trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14766","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":"2605.14766","created_at":"2026-05-17T23:38:58.700621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14766v1","created_at":"2026-05-17T23:38:58.700621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14766","created_at":"2026-05-17T23:38:58.700621+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACGMQEIHUJOT","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACGMQEIHUJOTZP7W","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACGMQEIH","created_at":"2026-05-18T12:33:37.589309+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/ACGMQEIHUJOTZP7WCTXM3A7YQJ","json":"https://pith.science/pith/ACGMQEIHUJOTZP7WCTXM3A7YQJ.json","graph_json":"https://pith.science/api/pith-number/ACGMQEIHUJOTZP7WCTXM3A7YQJ/graph.json","events_json":"https://pith.science/api/pith-number/ACGMQEIHUJOTZP7WCTXM3A7YQJ/events.json","paper":"https://pith.science/paper/ACGMQEIH"},"agent_actions":{"view_html":"https://pith.science/pith/ACGMQEIHUJOTZP7WCTXM3A7YQJ","download_json":"https://pith.science/pith/ACGMQEIHUJOTZP7WCTXM3A7YQJ.json","view_paper":"https://pith.science/paper/ACGMQEIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14766&json=true","fetch_graph":"https://pith.science/api/pith-number/ACGMQEIHUJOTZP7WCTXM3A7YQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ACGMQEIHUJOTZP7WCTXM3A7YQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACGMQEIHUJOTZP7WCTXM3A7YQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACGMQEIHUJOTZP7WCTXM3A7YQJ/action/storage_attestation","attest_author":"https://pith.science/pith/ACGMQEIHUJOTZP7WCTXM3A7YQJ/action/author_attestation","sign_citation":"https://pith.science/pith/ACGMQEIHUJOTZP7WCTXM3A7YQJ/action/citation_signature","submit_replication":"https://pith.science/pith/ACGMQEIHUJOTZP7WCTXM3A7YQJ/action/replication_record"}},"created_at":"2026-05-17T23:38:58.700621+00:00","updated_at":"2026-05-17T23:38:58.700621+00:00"}