{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L7KA6ZG5KVKVEFOKNBCKMBJOMQ","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":"66dad8be3ea10b7e58610903bc1b61b948a151bec36d331f996ffd6964717389","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":"2024-06-11T14:17:12Z","title_canon_sha256":"901ff4b81ddaf289f19abfe350223f304fefea096eae5db13ef87feefe0583ed"},"schema_version":"1.0","source":{"id":"2406.07289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07289","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07289v1","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07289","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"pith_short_12","alias_value":"L7KA6ZG5KVKV","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"pith_short_16","alias_value":"L7KA6ZG5KVKVEFOK","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"pith_short_8","alias_value":"L7KA6ZG5","created_at":"2026-07-05T08:30:21Z"}],"graph_snapshots":[{"event_id":"sha256:16438f6acbf418a550f8aa0f0b936ce415b4fdab709738cf98fa30a3d4f9e102","target":"graph","created_at":"2026-07-05T08:30:21Z","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/2406.07289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently proposed two-pass direct speech-to-speech translation (S2ST) models decompose the task into speech-to-text translation (S2TT) and text-to-speech (TTS) within an end-to-end model, yielding promising results. However, the training of these models still relies on parallel speech data, which is extremely challenging to collect. In contrast, S2TT and TTS have accumulated a large amount of data and pretrained models, which have not been fully utilized in the development of S2ST models. Inspired by this, in this paper, we first introduce a composite S2ST model named ComSpeech, which can seam","authors_text":"Min Zhang, Qingkai Fang, Shaolei Zhang, Yang Feng, Zhengrui Ma","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":"2024-06-11T14:17:12Z","title":"Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07289","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":"sha256:6fa337a3b23a27a9ac8fa76f201740aa999dcde0c134f6b3e3d22af342d0f21a","target":"record","created_at":"2026-07-05T08:30:21Z","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":"66dad8be3ea10b7e58610903bc1b61b948a151bec36d331f996ffd6964717389","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":"2024-06-11T14:17:12Z","title_canon_sha256":"901ff4b81ddaf289f19abfe350223f304fefea096eae5db13ef87feefe0583ed"},"schema_version":"1.0","source":{"id":"2406.07289","kind":"arxiv","version":1}},"canonical_sha256":"5fd40f64dd55555215ca6844a6052e64323a609d7aec51eaf5b6de921c9ef2b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fd40f64dd55555215ca6844a6052e64323a609d7aec51eaf5b6de921c9ef2b2","first_computed_at":"2026-07-05T08:30:21.194924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:21.194924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6IwoLETksR/YJr3ZJeKL4z1zD8kJQgpuhxYWfGdV7JKmWIaHFvW2/qkKJ+lYx/ERHlPyPvSy0H2Vsrb6Z8+FCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:21.195431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fa337a3b23a27a9ac8fa76f201740aa999dcde0c134f6b3e3d22af342d0f21a","sha256:16438f6acbf418a550f8aa0f0b936ce415b4fdab709738cf98fa30a3d4f9e102"],"state_sha256":"82fe47abe825394d8fa1d9f490adc93c175c7d8fd1150b077c4167266ee9d3aa"}