{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CLXWC6NP6D6DJDJBU3ITT2JGZQ","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":"3e36650d2b23aeaa11622990263738c5690cf6fbe8fe2c8db4ed9f8ad4128063","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-10T02:32:58Z","title_canon_sha256":"595c015952a42de239fd91473e325102e317c7760911b617d00e4f0967470f7d"},"schema_version":"1.0","source":{"id":"2404.06690","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06690","created_at":"2026-07-05T09:49:04Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06690v3","created_at":"2026-07-05T09:49:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06690","created_at":"2026-07-05T09:49:04Z"},{"alias_kind":"pith_short_12","alias_value":"CLXWC6NP6D6D","created_at":"2026-07-05T09:49:04Z"},{"alias_kind":"pith_short_16","alias_value":"CLXWC6NP6D6DJDJB","created_at":"2026-07-05T09:49:04Z"},{"alias_kind":"pith_short_8","alias_value":"CLXWC6NP","created_at":"2026-07-05T09:49:04Z"}],"graph_snapshots":[{"event_id":"sha256:21b16d4fae5f472cd4d377c80610230e592b8593b1d45f97d9d18d0d360f5560","target":"graph","created_at":"2026-07-05T09:49:04Z","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/2404.06690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-10T02:32:58Z","title":"CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06690","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:d41214126475d7132f8c44d2f4c69e6d8822d252c37d76f521d1078b23f349b3","target":"record","created_at":"2026-07-05T09:49:04Z","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":"3e36650d2b23aeaa11622990263738c5690cf6fbe8fe2c8db4ed9f8ad4128063","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-10T02:32:58Z","title_canon_sha256":"595c015952a42de239fd91473e325102e317c7760911b617d00e4f0967470f7d"},"schema_version":"1.0","source":{"id":"2404.06690","kind":"arxiv","version":3}},"canonical_sha256":"12ef6179aff0fc348d21a6d139e926cc15fdb1c6ac877655b49751ab4034a755","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12ef6179aff0fc348d21a6d139e926cc15fdb1c6ac877655b49751ab4034a755","first_computed_at":"2026-07-05T09:49:04.166299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:04.166299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9yVja9T97W4CM+EsHQwFwPnmJyioA+atL/cxfKQ1NCY4M4b15VhOGJMWe/DDOe+6O9fCPm474GmRTnXz8wDgCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:04.166738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06690","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d41214126475d7132f8c44d2f4c69e6d8822d252c37d76f521d1078b23f349b3","sha256:21b16d4fae5f472cd4d377c80610230e592b8593b1d45f97d9d18d0d360f5560"],"state_sha256":"75c24d4a59982bfb0d51b06a28e7c6577e5998ed82cfe2f862cbc062e065adc3"}