{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JQSKNTHSFTLM4M5T7Q5HX3ZZOD","short_pith_number":"pith:JQSKNTHS","canonical_record":{"source":{"id":"2405.17809","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T04:11:37Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"3d605e8b8525fcb04e55f5abf6acbfe9463ac74fd4c1bf23301fb1dbe98cf598","abstract_canon_sha256":"dc918c61a39344085c687d5ebc78e13c5deb9a7c3da3455009f9d35d0ab1846e"},"schema_version":"1.0"},"canonical_sha256":"4c24a6ccf22cd6ce33b3fc3a7bef3970fe8e223cca89f7b0633a349c0bfd97b5","source":{"kind":"arxiv","id":"2405.17809","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17809","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17809v3","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17809","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"pith_short_12","alias_value":"JQSKNTHSFTLM","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"pith_short_16","alias_value":"JQSKNTHSFTLM4M5T","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"pith_short_8","alias_value":"JQSKNTHS","created_at":"2026-07-05T09:28:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JQSKNTHSFTLM4M5T7Q5HX3ZZOD","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17809","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T04:11:37Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"3d605e8b8525fcb04e55f5abf6acbfe9463ac74fd4c1bf23301fb1dbe98cf598","abstract_canon_sha256":"dc918c61a39344085c687d5ebc78e13c5deb9a7c3da3455009f9d35d0ab1846e"},"schema_version":"1.0"},"canonical_sha256":"4c24a6ccf22cd6ce33b3fc3a7bef3970fe8e223cca89f7b0633a349c0bfd97b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:50.427723Z","signature_b64":"mi/L0jTFB+UI5a1BfPxXB8gI4dC0tKOJWb0tGEdyrYu++NB7QZcLym8eIdnvguVJESgIUvCYRm9FObhBnCKAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c24a6ccf22cd6ce33b3fc3a7bef3970fe8e223cca89f7b0633a349c0bfd97b5","last_reissued_at":"2026-07-05T09:28:50.427189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:50.427189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17809","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N963rC4wpwNuRJGuTSJwF+K7IDBo1XngufKr8wn3YVdb4dMhX+BG2uXij6xfn4rP1HF3OCILedRgjXFb5OVsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:46:11.121510Z"},"content_sha256":"3e9b652fe715f20eb36a05f118cda849975c9f40d3ec84414ac1a997280770b1","schema_version":"1.0","event_id":"sha256:3e9b652fe715f20eb36a05f118cda849975c9f40d3ec84414ac1a997280770b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JQSKNTHSFTLM4M5T7Q5HX3ZZOD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenyang Le, Dongmei Wang, Jinyu Li, Long Zhou, Michael Zeng, Midia Yousefi, Sheng Zhao, Shujie Liu, Xiaofei Wang, Yanmin Qian, Yao Qian","submitted_at":"2024-05-28T04:11:37Z","abstract_excerpt":"There is a rising interest and trend in research towards directly translating speech from one language to another, known as end-to-end speech-to-speech translation. However, most end-to-end models struggle to outperform cascade models, i.e., a pipeline framework by concatenating speech recognition, machine translation and text-to-speech models. The primary challenges stem from the inherent complexities involved in direct translation tasks and the scarcity of data. In this study, we introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion yet facilitates e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17809","kind":"arxiv","version":3},"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/2405.17809/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":"2026-07-05T09:28:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"64R/blBQ4M5oMnoPGt0t6LU/v7acm7ESXFEnrldvWr0X2bsgEwvKW3uK3IAYYOj5IsKs8d7dTEstBRVtti1EDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:46:11.122189Z"},"content_sha256":"608a6996f3689322042b0f0e76a067cbaf22f765fe4d74631917c258b518012a","schema_version":"1.0","event_id":"sha256:608a6996f3689322042b0f0e76a067cbaf22f765fe4d74631917c258b518012a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQSKNTHSFTLM4M5T7Q5HX3ZZOD/bundle.json","state_url":"https://pith.science/pith/JQSKNTHSFTLM4M5T7Q5HX3ZZOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQSKNTHSFTLM4M5T7Q5HX3ZZOD/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":"2026-08-18T16:46:11Z","links":{"resolver":"https://pith.science/pith/JQSKNTHSFTLM4M5T7Q5HX3ZZOD","bundle":"https://pith.science/pith/JQSKNTHSFTLM4M5T7Q5HX3ZZOD/bundle.json","state":"https://pith.science/pith/JQSKNTHSFTLM4M5T7Q5HX3ZZOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQSKNTHSFTLM4M5T7Q5HX3ZZOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JQSKNTHSFTLM4M5T7Q5HX3ZZOD","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":"dc918c61a39344085c687d5ebc78e13c5deb9a7c3da3455009f9d35d0ab1846e","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T04:11:37Z","title_canon_sha256":"3d605e8b8525fcb04e55f5abf6acbfe9463ac74fd4c1bf23301fb1dbe98cf598"},"schema_version":"1.0","source":{"id":"2405.17809","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17809","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17809v3","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17809","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"pith_short_12","alias_value":"JQSKNTHSFTLM","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"pith_short_16","alias_value":"JQSKNTHSFTLM4M5T","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"pith_short_8","alias_value":"JQSKNTHS","created_at":"2026-07-05T09:28:50Z"}],"graph_snapshots":[{"event_id":"sha256:608a6996f3689322042b0f0e76a067cbaf22f765fe4d74631917c258b518012a","target":"graph","created_at":"2026-07-05T09:28:50Z","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/2405.17809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a rising interest and trend in research towards directly translating speech from one language to another, known as end-to-end speech-to-speech translation. However, most end-to-end models struggle to outperform cascade models, i.e., a pipeline framework by concatenating speech recognition, machine translation and text-to-speech models. The primary challenges stem from the inherent complexities involved in direct translation tasks and the scarcity of data. In this study, we introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion yet facilitates e","authors_text":"Chenyang Le, Dongmei Wang, Jinyu Li, Long Zhou, Michael Zeng, Midia Yousefi, Sheng Zhao, Shujie Liu, Xiaofei Wang, Yanmin Qian, Yao Qian","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T04:11:37Z","title":"TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17809","kind":"arxiv","version":3},"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":"sha256:3e9b652fe715f20eb36a05f118cda849975c9f40d3ec84414ac1a997280770b1","target":"record","created_at":"2026-07-05T09:28:50Z","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":"dc918c61a39344085c687d5ebc78e13c5deb9a7c3da3455009f9d35d0ab1846e","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T04:11:37Z","title_canon_sha256":"3d605e8b8525fcb04e55f5abf6acbfe9463ac74fd4c1bf23301fb1dbe98cf598"},"schema_version":"1.0","source":{"id":"2405.17809","kind":"arxiv","version":3}},"canonical_sha256":"4c24a6ccf22cd6ce33b3fc3a7bef3970fe8e223cca89f7b0633a349c0bfd97b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c24a6ccf22cd6ce33b3fc3a7bef3970fe8e223cca89f7b0633a349c0bfd97b5","first_computed_at":"2026-07-05T09:28:50.427189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:50.427189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mi/L0jTFB+UI5a1BfPxXB8gI4dC0tKOJWb0tGEdyrYu++NB7QZcLym8eIdnvguVJESgIUvCYRm9FObhBnCKAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:50.427723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17809","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e9b652fe715f20eb36a05f118cda849975c9f40d3ec84414ac1a997280770b1","sha256:608a6996f3689322042b0f0e76a067cbaf22f765fe4d74631917c258b518012a"],"state_sha256":"daeb7c734cde9411d08831c8202138ba3ee3ec6bfbc5be6a27a48cd75693577f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XH+Rev5+F1ek6WebX+UA8sE5aScn3wTr9uctw7mNkDMZMi46CESuBEL/P6NrDbQyaBXk7gUCVAfV4DYt+mZ5Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:46:11.129820Z","bundle_sha256":"dc81d5ebe9ae237ee8ddbfc6e90181dcd3e33f58e7047bc2bc637565a901ace9"}}