{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GZNTQLVBKXPE4LBM3Y4LVKR4H2","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":"54d4af5e5a0b4b15cb158c07f3f05cc8b57e31846625b9436073949219aeff4b","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-02-08T17:34:32Z","title_canon_sha256":"8d5e7981fd02bc9bbc3d3427f6d205f74a0f4a3a564b662257e2529415c76307"},"schema_version":"1.0","source":{"id":"2302.04215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04215","created_at":"2026-07-05T05:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04215v1","created_at":"2026-07-05T05:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04215","created_at":"2026-07-05T05:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"GZNTQLVBKXPE","created_at":"2026-07-05T05:40:02Z"},{"alias_kind":"pith_short_16","alias_value":"GZNTQLVBKXPE4LBM","created_at":"2026-07-05T05:40:02Z"},{"alias_kind":"pith_short_8","alias_value":"GZNTQLVB","created_at":"2026-07-05T05:40:02Z"}],"graph_snapshots":[{"event_id":"sha256:44aa3963f0f5a8536f0789468ab4f4b27d32c0e608ab58cb6cec596ccecf584d","target":"graph","created_at":"2026-07-05T05:40:02Z","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/2302.04215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Text-to-Speech (TTS) systems trained on reading or acted corpora have achieved near human-level naturalness. The diversity of human speech, however, often goes beyond the coverage of these corpora. We believe the ability to handle such diversity is crucial for AI systems to achieve human-level communication. Our work explores the use of more abundant real-world data for building speech synthesizers. We train TTS systems using real-world speech from YouTube and podcasts. We observe the mismatch between training and inference alignments in mel-spectrogram based autoregressive models, lead","authors_text":"Alexander Rudnicky, Li-Wei Chen, Shinji Watanabe","cross_cats":["cs.AI","cs.LG","cs.SD","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-02-08T17:34:32Z","title":"A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04215","kind":"arxiv","version":1},"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":"sha256:15857d69a63158afe039a0dfa86a492da156ba066fbbd57ea07ae6f47cb508bd","target":"record","created_at":"2026-07-05T05:40:02Z","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":"54d4af5e5a0b4b15cb158c07f3f05cc8b57e31846625b9436073949219aeff4b","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-02-08T17:34:32Z","title_canon_sha256":"8d5e7981fd02bc9bbc3d3427f6d205f74a0f4a3a564b662257e2529415c76307"},"schema_version":"1.0","source":{"id":"2302.04215","kind":"arxiv","version":1}},"canonical_sha256":"365b382ea155de4e2c2cde38baaa3c3eabd0809744db869f5d185a760f0ee052","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"365b382ea155de4e2c2cde38baaa3c3eabd0809744db869f5d185a760f0ee052","first_computed_at":"2026-07-05T05:40:02.140485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:02.140485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+MNM3oKrkPFmAxYOzYchpfzTwxxqOpGXebt/A+RGz6cJeBMA7oO6Bn80bBL00A1tRQ8GJt9EOjuosmW0vm7aAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:02.140853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.04215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15857d69a63158afe039a0dfa86a492da156ba066fbbd57ea07ae6f47cb508bd","sha256:44aa3963f0f5a8536f0789468ab4f4b27d32c0e608ab58cb6cec596ccecf584d"],"state_sha256":"197c0ace29f95d5dc449f3ee00669e3e09f1597f9f2c21c34b466e956caf4e01"}