{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CLXWC6NP6D6DJDJBU3ITT2JGZQ","short_pith_number":"pith:CLXWC6NP","schema_version":"1.0","canonical_sha256":"12ef6179aff0fc348d21a6d139e926cc15fdb1c6ac877655b49751ab4034a755","source":{"kind":"arxiv","id":"2404.06690","version":3},"attestation_state":"computed","paper":{"title":"CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongmei Wang, Jinyu Li, Lei He, Leying Zhang, Long Zhou, Michael Zeng, Midia Yousefi, Sheng Zhao, Shujie Liu, Xiaofei Wang, Yanmin Qian, Yao Qian","submitted_at":"2024-04-10T02:32:58Z","abstract_excerpt":"Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along with achieving human-like naturalness in speech, continues to be a challenge. In this paper, we introduce CoVoMix: Conversational Voice Mixture Generation, a novel model for zero-shot, human-like, multi-speaker, multi-round dialogue speech generation. CoVoMix first converts dialogue text into multiple streams of discrete tokens, with each token stream representing semantic information for individual talkers. These tok"},"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":"2404.06690","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-10T02:32:58Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"595c015952a42de239fd91473e325102e317c7760911b617d00e4f0967470f7d","abstract_canon_sha256":"3e36650d2b23aeaa11622990263738c5690cf6fbe8fe2c8db4ed9f8ad4128063"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:04.166738Z","signature_b64":"9yVja9T97W4CM+EsHQwFwPnmJyioA+atL/cxfKQ1NCY4M4b15VhOGJMWe/DDOe+6O9fCPm474GmRTnXz8wDgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ef6179aff0fc348d21a6d139e926cc15fdb1c6ac877655b49751ab4034a755","last_reissued_at":"2026-07-05T09:49:04.166299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:04.166299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongmei Wang, Jinyu Li, Lei He, Leying Zhang, Long Zhou, Michael Zeng, Midia Yousefi, Sheng Zhao, Shujie Liu, Xiaofei Wang, Yanmin Qian, Yao Qian","submitted_at":"2024-04-10T02:32:58Z","abstract_excerpt":"Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along with achieving human-like naturalness in speech, continues to be a challenge. In this paper, we introduce CoVoMix: Conversational Voice Mixture Generation, a novel model for zero-shot, human-like, multi-speaker, multi-round dialogue speech generation. CoVoMix first converts dialogue text into multiple streams of discrete tokens, with each token stream representing semantic information for individual talkers. These tok"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06690","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/2404.06690/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":"2404.06690","created_at":"2026-07-05T09:49:04.166374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06690v3","created_at":"2026-07-05T09:49:04.166374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06690","created_at":"2026-07-05T09:49:04.166374+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLXWC6NP6D6D","created_at":"2026-07-05T09:49:04.166374+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLXWC6NP6D6DJDJB","created_at":"2026-07-05T09:49:04.166374+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLXWC6NP","created_at":"2026-07-05T09:49:04.166374+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/CLXWC6NP6D6DJDJBU3ITT2JGZQ","json":"https://pith.science/pith/CLXWC6NP6D6DJDJBU3ITT2JGZQ.json","graph_json":"https://pith.science/api/pith-number/CLXWC6NP6D6DJDJBU3ITT2JGZQ/graph.json","events_json":"https://pith.science/api/pith-number/CLXWC6NP6D6DJDJBU3ITT2JGZQ/events.json","paper":"https://pith.science/paper/CLXWC6NP"},"agent_actions":{"view_html":"https://pith.science/pith/CLXWC6NP6D6DJDJBU3ITT2JGZQ","download_json":"https://pith.science/pith/CLXWC6NP6D6DJDJBU3ITT2JGZQ.json","view_paper":"https://pith.science/paper/CLXWC6NP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06690&json=true","fetch_graph":"https://pith.science/api/pith-number/CLXWC6NP6D6DJDJBU3ITT2JGZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CLXWC6NP6D6DJDJBU3ITT2JGZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLXWC6NP6D6DJDJBU3ITT2JGZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLXWC6NP6D6DJDJBU3ITT2JGZQ/action/storage_attestation","attest_author":"https://pith.science/pith/CLXWC6NP6D6DJDJBU3ITT2JGZQ/action/author_attestation","sign_citation":"https://pith.science/pith/CLXWC6NP6D6DJDJBU3ITT2JGZQ/action/citation_signature","submit_replication":"https://pith.science/pith/CLXWC6NP6D6DJDJBU3ITT2JGZQ/action/replication_record"}},"created_at":"2026-07-05T09:49:04.166374+00:00","updated_at":"2026-07-05T09:49:04.166374+00:00"}