{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VQ342OQISRN7JVARDPOGQTYLHS","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":"247caa43930de93a6b3b294d2361fd93c20c11b9842e997b52b1a8e43b40f460","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-16T02:48:17Z","title_canon_sha256":"2e4e4aff975b9b72b7295de67ac608f71119800c114342f20d7743c8b80f26da"},"schema_version":"1.0","source":{"id":"2506.13053","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13053","created_at":"2026-07-05T11:49:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13053v3","created_at":"2026-07-05T11:49:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13053","created_at":"2026-07-05T11:49:55Z"},{"alias_kind":"pith_short_12","alias_value":"VQ342OQISRN7","created_at":"2026-07-05T11:49:55Z"},{"alias_kind":"pith_short_16","alias_value":"VQ342OQISRN7JVAR","created_at":"2026-07-05T11:49:55Z"},{"alias_kind":"pith_short_8","alias_value":"VQ342OQI","created_at":"2026-07-05T11:49:55Z"}],"graph_snapshots":[{"event_id":"sha256:077bde42205a3e4baa2b97928859001ac9c8ffcc99986efe9978f88513865d12","target":"graph","created_at":"2026-07-05T11:49:55Z","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/2506.13053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing large-scale zero-shot text-to-speech (TTS) models deliver high speech quality but suffer from slow inference speeds due to massive parameters. To address this issue, this paper introduces ZipVoice, a high-quality flow-matching-based zero-shot TTS model with a compact model size and fast inference speed. Key designs include: 1) a Zipformer-based vector field estimator to maintain adequate modeling capabilities under constrained size; 2) Average upsampling-based initial speech-text alignment and Zipformer-based text encoder to improve speech intelligibility; 3) A flow distillation metho","authors_text":"Daniel Povey, Fangjun Kuang, Han Zhu, Liyong Guo, Long Lin, Weiji Zhuang, Wei Kang, Zengwei Yao, Zhaoqing Li","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-16T02:48:17Z","title":"ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13053","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":"sha256:91724eab183119835cb9cbaee315654ac9243e732a3ee496a8aa1bb73e11dabc","target":"record","created_at":"2026-07-05T11:49:55Z","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":"247caa43930de93a6b3b294d2361fd93c20c11b9842e997b52b1a8e43b40f460","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-16T02:48:17Z","title_canon_sha256":"2e4e4aff975b9b72b7295de67ac608f71119800c114342f20d7743c8b80f26da"},"schema_version":"1.0","source":{"id":"2506.13053","kind":"arxiv","version":3}},"canonical_sha256":"ac37cd3a08945bf4d4111bdc684f0b3c972741d76a6b039b45f2308f6f3655cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac37cd3a08945bf4d4111bdc684f0b3c972741d76a6b039b45f2308f6f3655cc","first_computed_at":"2026-07-05T11:49:55.660776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:55.660776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R1CVvVZmWqwoDxi2FGbUJUkF9/sRXBLiiXBFbi3QaU5T/PI+ragC+0koOTjvSpwaQDwXSVe0ZK5FZf6iCVshAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:55.661263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.13053","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91724eab183119835cb9cbaee315654ac9243e732a3ee496a8aa1bb73e11dabc","sha256:077bde42205a3e4baa2b97928859001ac9c8ffcc99986efe9978f88513865d12"],"state_sha256":"1db69ac3dd495bf494564f2af8c1654b7f173ead46be86dfe668d97c177cd8cf"}