{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H5U7WANXQED4VJAZ6BGR5HS5V5","short_pith_number":"pith:H5U7WANX","canonical_record":{"source":{"id":"2410.03298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T10:21:15Z","cross_cats_sorted":[],"title_canon_sha256":"f6acb4b5c200d05c7cb6d8427a318240bb2e17fab27f43886127a7907a716f4a","abstract_canon_sha256":"0b14350d5e648201cd421e4d7b425d257c513ac92c7ec32abcb3645bd6ba7ffe"},"schema_version":"1.0"},"canonical_sha256":"3f69fb01b78107caa419f04d1e9e5daf557be08fe270738590eee384e02dac8f","source":{"kind":"arxiv","id":"2410.03298","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03298","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03298v1","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03298","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"H5U7WANXQED4","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"H5U7WANXQED4VJAZ","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"H5U7WANX","created_at":"2026-07-05T09:15:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H5U7WANXQED4VJAZ6BGR5HS5V5","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T10:21:15Z","cross_cats_sorted":[],"title_canon_sha256":"f6acb4b5c200d05c7cb6d8427a318240bb2e17fab27f43886127a7907a716f4a","abstract_canon_sha256":"0b14350d5e648201cd421e4d7b425d257c513ac92c7ec32abcb3645bd6ba7ffe"},"schema_version":"1.0"},"canonical_sha256":"3f69fb01b78107caa419f04d1e9e5daf557be08fe270738590eee384e02dac8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:47.353957Z","signature_b64":"IUhwdUPb2iiurvQEEqWLChVa0JUEKmMxt/46a8xqdCVZ+wanOqA+jyLRY/nDNbwedC7m6i/cwwVItfmw/BxXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f69fb01b78107caa419f04d1e9e5daf557be08fe270738590eee384e02dac8f","last_reissued_at":"2026-07-05T09:15:47.353442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:47.353442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03298","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6UlkElvahPLOOR19+CX1k7QF8dOarP1Z8VYRVsgulwnNAqY72a7s2lLJPg+WDqaOLHZazni81nvAlGtbwreDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T02:20:32.690024Z"},"content_sha256":"d334fdecd90c4230f5d2ed7e7f3903a209eab8ee2b720af0aa9161567b5103f7","schema_version":"1.0","event_id":"sha256:d334fdecd90c4230f5d2ed7e7f3903a209eab8ee2b720af0aa9161567b5103f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H5U7WANXQED4VJAZ6BGR5HS5V5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Christian Fuegen, Duc Le, Egor Lakomkin, Jinzheng Zhao, Katerina Zmolikova, Niko Moritz, Ruiming Xie, Yashesh Gaur, Zeeshan Ahmed, Zhiping Xiu","submitted_at":"2024-10-04T10:21:15Z","abstract_excerpt":"Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech translation model that outputs discrete speech tokens in a low-latency streaming fashion. This approach eliminates the need for generating text output first, followed by machine translation (MT) and text-to-speech (TTS) systems. The produced speech tokens can be directly used to generate a speech signal with low latency by utilizing an acoustic language model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03298","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/2410.03298/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gK8k9G3+4qp8smliJ5iwv+Rij370ioxFXf4z4eLx7gTm2EWTypqmQvjV+XZ1MzAYmY72ZSksUhVd0vlnqMF3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T02:20:32.690628Z"},"content_sha256":"bebe0e6e9c5bcb2e7614fb09c3e0b4e38606802e8f58fa2009666c7e1b951401","schema_version":"1.0","event_id":"sha256:bebe0e6e9c5bcb2e7614fb09c3e0b4e38606802e8f58fa2009666c7e1b951401"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/bundle.json","state_url":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T02:20:32Z","links":{"resolver":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5","bundle":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/bundle.json","state":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H5U7WANXQED4VJAZ6BGR5HS5V5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0b14350d5e648201cd421e4d7b425d257c513ac92c7ec32abcb3645bd6ba7ffe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T10:21:15Z","title_canon_sha256":"f6acb4b5c200d05c7cb6d8427a318240bb2e17fab27f43886127a7907a716f4a"},"schema_version":"1.0","source":{"id":"2410.03298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03298","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03298v1","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03298","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"H5U7WANXQED4","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"H5U7WANXQED4VJAZ","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"H5U7WANX","created_at":"2026-07-05T09:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:bebe0e6e9c5bcb2e7614fb09c3e0b4e38606802e8f58fa2009666c7e1b951401","target":"graph","created_at":"2026-07-05T09:15:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.03298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech translation model that outputs discrete speech tokens in a low-latency streaming fashion. This approach eliminates the need for generating text output first, followed by machine translation (MT) and text-to-speech (TTS) systems. The produced speech tokens can be directly used to generate a speech signal with low latency by utilizing an acoustic language model ","authors_text":"Christian Fuegen, Duc Le, Egor Lakomkin, Jinzheng Zhao, Katerina Zmolikova, Niko Moritz, Ruiming Xie, Yashesh Gaur, Zeeshan Ahmed, Zhiping Xiu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T10:21:15Z","title":"Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03298","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d334fdecd90c4230f5d2ed7e7f3903a209eab8ee2b720af0aa9161567b5103f7","target":"record","created_at":"2026-07-05T09:15:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0b14350d5e648201cd421e4d7b425d257c513ac92c7ec32abcb3645bd6ba7ffe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T10:21:15Z","title_canon_sha256":"f6acb4b5c200d05c7cb6d8427a318240bb2e17fab27f43886127a7907a716f4a"},"schema_version":"1.0","source":{"id":"2410.03298","kind":"arxiv","version":1}},"canonical_sha256":"3f69fb01b78107caa419f04d1e9e5daf557be08fe270738590eee384e02dac8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f69fb01b78107caa419f04d1e9e5daf557be08fe270738590eee384e02dac8f","first_computed_at":"2026-07-05T09:15:47.353442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:47.353442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IUhwdUPb2iiurvQEEqWLChVa0JUEKmMxt/46a8xqdCVZ+wanOqA+jyLRY/nDNbwedC7m6i/cwwVItfmw/BxXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:47.353957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d334fdecd90c4230f5d2ed7e7f3903a209eab8ee2b720af0aa9161567b5103f7","sha256:bebe0e6e9c5bcb2e7614fb09c3e0b4e38606802e8f58fa2009666c7e1b951401"],"state_sha256":"fd58545b75534c6f4e5707a9234087839a9f21b9126a850ba1c9bbf30ec862c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ABsNO6IdfjFGQVS5PzEJRfkV/q+Tof1gP+CUV7rA4Mn9V41oJdulaYOeTSWYcpgDjskkIkGeV15hhID5enEADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T02:20:32.695810Z","bundle_sha256":"050a45ca1986d1686f800c9311397998b468e4d03cd6006d3be0e23cbd762346"}}