{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RVE46NHJ2ID5XR7PRJX3MDXI7T","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":"a62f349476f8fd72c65188a98e4134f61000521957f5d51514d3783641290e0d","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-22T02:54:15Z","title_canon_sha256":"36452a716581f0a2e60e76d63b39a04245c06ca7704027a909e392c59246f306"},"schema_version":"1.0","source":{"id":"2312.14398","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14398","created_at":"2026-07-05T08:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14398v2","created_at":"2026-07-05T08:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14398","created_at":"2026-07-05T08:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"RVE46NHJ2ID5","created_at":"2026-07-05T08:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"RVE46NHJ2ID5XR7P","created_at":"2026-07-05T08:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"RVE46NHJ","created_at":"2026-07-05T08:59:25Z"}],"graph_snapshots":[{"event_id":"sha256:c3456864262d61847fc51bec30eae45579a9a5fbdaf5a2c67e0d53930fbefeb4","target":"graph","created_at":"2026-07-05T08:59:25Z","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/2312.14398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality audio data. TTS systems are typically built using a single speaker's voices, but there is growing interest in developing systems that can synthesize voices for new speakers using only a few seconds of their speech. This paper presents ZMM-TTS, a multilingual and multispeaker framework utilizing quantized latent speech representations from a large-scale, pre-trai","authors_text":"Cheng Gong, Dan Wells, Erica Cooper, Jianwu Dang, Junichi Yamagishi, Korin Richmond, Longbiao Wang, Xin Wang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-22T02:54:15Z","title":"ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14398","kind":"arxiv","version":2},"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:cab9c306a0b601db79fb831582738d7d9702777a37857b4ab5690ec8acd51db0","target":"record","created_at":"2026-07-05T08:59:25Z","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":"a62f349476f8fd72c65188a98e4134f61000521957f5d51514d3783641290e0d","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-22T02:54:15Z","title_canon_sha256":"36452a716581f0a2e60e76d63b39a04245c06ca7704027a909e392c59246f306"},"schema_version":"1.0","source":{"id":"2312.14398","kind":"arxiv","version":2}},"canonical_sha256":"8d49cf34e9d207dbc7ef8a6fb60ee8fccfda1d3f113ae06298162632aa8774f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d49cf34e9d207dbc7ef8a6fb60ee8fccfda1d3f113ae06298162632aa8774f7","first_computed_at":"2026-07-05T08:59:25.203882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:25.203882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"830joIwq6VeFswo2wMJCP0uiHo5CI9uPn46Ff0G75Ryu2xiR7tTahxUMbU15/bIOiFVeRzI8c8/gagn4KoG/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:25.204473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14398","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cab9c306a0b601db79fb831582738d7d9702777a37857b4ab5690ec8acd51db0","sha256:c3456864262d61847fc51bec30eae45579a9a5fbdaf5a2c67e0d53930fbefeb4"],"state_sha256":"03bf65724a392a9e0ea1f1c6c64ff35cac176a53407df68ef5c2be5a47788d14"}