{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E7UUPQYMATE7K7RZZ5USSOF55M","short_pith_number":"pith:E7UUPQYM","schema_version":"1.0","canonical_sha256":"27e947c30c04c9f57e39cf692938bdeb16bdb946554f3fa7c8da2e87b4c1adfd","source":{"kind":"arxiv","id":"2508.13358","version":1},"attestation_state":"computed","paper":{"title":"Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christian Fuegen, Frank Seide, Ju Lin, Niko Moritz, Ruiming Xie, Simone Merello, Zeeshan Ahmed, Zhe Liu","submitted_at":"2025-08-18T21:00:11Z","abstract_excerpt":"This paper tackles several challenges that arise when integrating Automatic Speech Recognition (ASR) and Machine Translation (MT) for real-time, on-device streaming speech translation. Although state-of-the-art ASR systems based on Recurrent Neural Network Transducers (RNN-T) can perform real-time transcription, achieving streaming translation in real-time remains a significant challenge. To address this issue, we propose a simultaneous translation approach that effectively balances translation quality and latency. We also investigate efficient integration of ASR and MT, leveraging linguistic "},"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":"2508.13358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T21:00:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8e703b2b9479f9d7e4324e9ad6b33494ed45338448bc11932c0f5d7d01b3763","abstract_canon_sha256":"748f88de76301b45932b5c9439553aed83ea78bd0c9aec4ef135246f7a636a86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:46.900617Z","signature_b64":"+0YmdRp3tZksSGyxkblSGxgDraqiw0AfEMxAsrj6BZKSvxvM+m/lbHaW4QeBA9c1VOHUYRY93REBTo27vWPrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27e947c30c04c9f57e39cf692938bdeb16bdb946554f3fa7c8da2e87b4c1adfd","last_reissued_at":"2026-07-05T11:55:46.900135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:46.900135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christian Fuegen, Frank Seide, Ju Lin, Niko Moritz, Ruiming Xie, Simone Merello, Zeeshan Ahmed, Zhe Liu","submitted_at":"2025-08-18T21:00:11Z","abstract_excerpt":"This paper tackles several challenges that arise when integrating Automatic Speech Recognition (ASR) and Machine Translation (MT) for real-time, on-device streaming speech translation. Although state-of-the-art ASR systems based on Recurrent Neural Network Transducers (RNN-T) can perform real-time transcription, achieving streaming translation in real-time remains a significant challenge. To address this issue, we propose a simultaneous translation approach that effectively balances translation quality and latency. We also investigate efficient integration of ASR and MT, leveraging linguistic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13358","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/2508.13358/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":"2508.13358","created_at":"2026-07-05T11:55:46.900193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13358v1","created_at":"2026-07-05T11:55:46.900193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13358","created_at":"2026-07-05T11:55:46.900193+00:00"},{"alias_kind":"pith_short_12","alias_value":"E7UUPQYMATE7","created_at":"2026-07-05T11:55:46.900193+00:00"},{"alias_kind":"pith_short_16","alias_value":"E7UUPQYMATE7K7RZ","created_at":"2026-07-05T11:55:46.900193+00:00"},{"alias_kind":"pith_short_8","alias_value":"E7UUPQYM","created_at":"2026-07-05T11:55:46.900193+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/E7UUPQYMATE7K7RZZ5USSOF55M","json":"https://pith.science/pith/E7UUPQYMATE7K7RZZ5USSOF55M.json","graph_json":"https://pith.science/api/pith-number/E7UUPQYMATE7K7RZZ5USSOF55M/graph.json","events_json":"https://pith.science/api/pith-number/E7UUPQYMATE7K7RZZ5USSOF55M/events.json","paper":"https://pith.science/paper/E7UUPQYM"},"agent_actions":{"view_html":"https://pith.science/pith/E7UUPQYMATE7K7RZZ5USSOF55M","download_json":"https://pith.science/pith/E7UUPQYMATE7K7RZZ5USSOF55M.json","view_paper":"https://pith.science/paper/E7UUPQYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13358&json=true","fetch_graph":"https://pith.science/api/pith-number/E7UUPQYMATE7K7RZZ5USSOF55M/graph.json","fetch_events":"https://pith.science/api/pith-number/E7UUPQYMATE7K7RZZ5USSOF55M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E7UUPQYMATE7K7RZZ5USSOF55M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E7UUPQYMATE7K7RZZ5USSOF55M/action/storage_attestation","attest_author":"https://pith.science/pith/E7UUPQYMATE7K7RZZ5USSOF55M/action/author_attestation","sign_citation":"https://pith.science/pith/E7UUPQYMATE7K7RZZ5USSOF55M/action/citation_signature","submit_replication":"https://pith.science/pith/E7UUPQYMATE7K7RZZ5USSOF55M/action/replication_record"}},"created_at":"2026-07-05T11:55:46.900193+00:00","updated_at":"2026-07-05T11:55:46.900193+00:00"}