{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:33N6KZNVFGCCJTZW6KUYXKUTM5","short_pith_number":"pith:33N6KZNV","schema_version":"1.0","canonical_sha256":"dedbe565b5298424cf36f2a98baa9367476b319b7ab15bcc57a6774f19a86e1c","source":{"kind":"arxiv","id":"2310.07403","version":1},"attestation_state":"computed","paper":{"title":"DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation","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":"Qingkai Fang, Yang Feng, Yan Zhou","submitted_at":"2023-10-11T11:39:36Z","abstract_excerpt":"Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal distribution, posing challenges to achieving both high-quality translations and fast decoding speeds for S2ST models. In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST. To better capture the complex distribution of the target speech, DASpeech adopts the two-pass architecture to decompose the generat"},"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":"2310.07403","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T11:39:36Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"c34ef927fa36b046d38e691cacaa2d1dd4a3a62d607c8b53c005a5c5c2f4eb9c","abstract_canon_sha256":"1e0f14466735d0072b29ca89b4a703fc11e22bc46376aae846a6bea774cf34ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:45.310354Z","signature_b64":"7QyJuvCp1Qhr0mDjjTxTpsPoqgL5vucHlajKQIbIXSG4v+cq+hErSlsDgZCgaih1rPZU703CuaNA+aEBw+IeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dedbe565b5298424cf36f2a98baa9367476b319b7ab15bcc57a6774f19a86e1c","last_reissued_at":"2026-07-05T06:59:45.309949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:45.309949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation","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":"Qingkai Fang, Yang Feng, Yan Zhou","submitted_at":"2023-10-11T11:39:36Z","abstract_excerpt":"Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal distribution, posing challenges to achieving both high-quality translations and fast decoding speeds for S2ST models. In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST. To better capture the complex distribution of the target speech, DASpeech adopts the two-pass architecture to decompose the generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07403","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/2310.07403/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":"2310.07403","created_at":"2026-07-05T06:59:45.310003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07403v1","created_at":"2026-07-05T06:59:45.310003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07403","created_at":"2026-07-05T06:59:45.310003+00:00"},{"alias_kind":"pith_short_12","alias_value":"33N6KZNVFGCC","created_at":"2026-07-05T06:59:45.310003+00:00"},{"alias_kind":"pith_short_16","alias_value":"33N6KZNVFGCCJTZW","created_at":"2026-07-05T06:59:45.310003+00:00"},{"alias_kind":"pith_short_8","alias_value":"33N6KZNV","created_at":"2026-07-05T06:59:45.310003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15333","citing_title":"Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/33N6KZNVFGCCJTZW6KUYXKUTM5","json":"https://pith.science/pith/33N6KZNVFGCCJTZW6KUYXKUTM5.json","graph_json":"https://pith.science/api/pith-number/33N6KZNVFGCCJTZW6KUYXKUTM5/graph.json","events_json":"https://pith.science/api/pith-number/33N6KZNVFGCCJTZW6KUYXKUTM5/events.json","paper":"https://pith.science/paper/33N6KZNV"},"agent_actions":{"view_html":"https://pith.science/pith/33N6KZNVFGCCJTZW6KUYXKUTM5","download_json":"https://pith.science/pith/33N6KZNVFGCCJTZW6KUYXKUTM5.json","view_paper":"https://pith.science/paper/33N6KZNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07403&json=true","fetch_graph":"https://pith.science/api/pith-number/33N6KZNVFGCCJTZW6KUYXKUTM5/graph.json","fetch_events":"https://pith.science/api/pith-number/33N6KZNVFGCCJTZW6KUYXKUTM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33N6KZNVFGCCJTZW6KUYXKUTM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33N6KZNVFGCCJTZW6KUYXKUTM5/action/storage_attestation","attest_author":"https://pith.science/pith/33N6KZNVFGCCJTZW6KUYXKUTM5/action/author_attestation","sign_citation":"https://pith.science/pith/33N6KZNVFGCCJTZW6KUYXKUTM5/action/citation_signature","submit_replication":"https://pith.science/pith/33N6KZNVFGCCJTZW6KUYXKUTM5/action/replication_record"}},"created_at":"2026-07-05T06:59:45.310003+00:00","updated_at":"2026-07-05T06:59:45.310003+00:00"}