{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MIXZE32TZGH2UNGZX66SK67ET4","short_pith_number":"pith:MIXZE32T","schema_version":"1.0","canonical_sha256":"622f926f53c98faa34d9bfbd257be49f074eee9698c46ea410919627920023ad","source":{"kind":"arxiv","id":"2306.02982","version":2},"attestation_state":"computed","paper":{"title":"PolyVoice: Language Models for Speech to Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Xu, Fengpeng Yue, Kexin Wang, Lu Lu, Mingxuan Wang, Qianqian Dong, Qiao Tian, Siyuan Feng, Tang Li, Tom Ko, Xi Chen, Xuxin Cheng, Ye Bai, Yunlong Zhao, Yuping Wang, Yuxuan Wang, Zejun Ma, Zhiying Huang","submitted_at":"2023-06-05T15:53:15Z","abstract_excerpt":"We propose PolyVoice, a language model-based framework for speech-to-speech translation (S2ST) system. Our framework consists of two language models: a translation language model and a speech synthesis language model. We use discretized speech units, which are generated in a fully unsupervised way, and thus our framework can be used for unwritten languages. For the speech synthesis part, we adopt the existing VALL-E X approach and build a unit-based audio language model. This grants our framework the ability to preserve the voice characteristics and the speaking style of the original speech. W"},"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":"2306.02982","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T15:53:15Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ffe58f8b02c8824e9bb0bf6904a28fc70ebfac682fbd49e0ebe0c10909597c3e","abstract_canon_sha256":"beae40f08f51b42567f2028f8e07f124ca3d7dea6db92e018e7b7255ea5ca3c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:59.569468Z","signature_b64":"ho04NET0cg+S+ooiHvilR1nzQf2RjS9AoeCNZ0F06eQUhKBZFnB/YJKUkQszN9uSTlhzT8YLaLDh1bgA4J7dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"622f926f53c98faa34d9bfbd257be49f074eee9698c46ea410919627920023ad","last_reissued_at":"2026-07-05T06:19:59.569040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:59.569040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolyVoice: Language Models for Speech to Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Xu, Fengpeng Yue, Kexin Wang, Lu Lu, Mingxuan Wang, Qianqian Dong, Qiao Tian, Siyuan Feng, Tang Li, Tom Ko, Xi Chen, Xuxin Cheng, Ye Bai, Yunlong Zhao, Yuping Wang, Yuxuan Wang, Zejun Ma, Zhiying Huang","submitted_at":"2023-06-05T15:53:15Z","abstract_excerpt":"We propose PolyVoice, a language model-based framework for speech-to-speech translation (S2ST) system. Our framework consists of two language models: a translation language model and a speech synthesis language model. We use discretized speech units, which are generated in a fully unsupervised way, and thus our framework can be used for unwritten languages. For the speech synthesis part, we adopt the existing VALL-E X approach and build a unit-based audio language model. This grants our framework the ability to preserve the voice characteristics and the speaking style of the original speech. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02982","kind":"arxiv","version":2},"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/2306.02982/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":"2306.02982","created_at":"2026-07-05T06:19:59.569096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02982v2","created_at":"2026-07-05T06:19:59.569096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02982","created_at":"2026-07-05T06:19:59.569096+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIXZE32TZGH2","created_at":"2026-07-05T06:19:59.569096+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIXZE32TZGH2UNGZ","created_at":"2026-07-05T06:19:59.569096+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIXZE32T","created_at":"2026-07-05T06:19:59.569096+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/MIXZE32TZGH2UNGZX66SK67ET4","json":"https://pith.science/pith/MIXZE32TZGH2UNGZX66SK67ET4.json","graph_json":"https://pith.science/api/pith-number/MIXZE32TZGH2UNGZX66SK67ET4/graph.json","events_json":"https://pith.science/api/pith-number/MIXZE32TZGH2UNGZX66SK67ET4/events.json","paper":"https://pith.science/paper/MIXZE32T"},"agent_actions":{"view_html":"https://pith.science/pith/MIXZE32TZGH2UNGZX66SK67ET4","download_json":"https://pith.science/pith/MIXZE32TZGH2UNGZX66SK67ET4.json","view_paper":"https://pith.science/paper/MIXZE32T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02982&json=true","fetch_graph":"https://pith.science/api/pith-number/MIXZE32TZGH2UNGZX66SK67ET4/graph.json","fetch_events":"https://pith.science/api/pith-number/MIXZE32TZGH2UNGZX66SK67ET4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIXZE32TZGH2UNGZX66SK67ET4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIXZE32TZGH2UNGZX66SK67ET4/action/storage_attestation","attest_author":"https://pith.science/pith/MIXZE32TZGH2UNGZX66SK67ET4/action/author_attestation","sign_citation":"https://pith.science/pith/MIXZE32TZGH2UNGZX66SK67ET4/action/citation_signature","submit_replication":"https://pith.science/pith/MIXZE32TZGH2UNGZX66SK67ET4/action/replication_record"}},"created_at":"2026-07-05T06:19:59.569096+00:00","updated_at":"2026-07-05T06:19:59.569096+00:00"}