{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_e55a5060477502c65b1783b010f6a5a0f8037722c6dd9eabbf58870a6d28e530","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_e55a5060477502c65b1783b010f6a5a0f8037722c6dd9eabbf58870a6d28e530","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"f4e01ed36009ac3b904af2cc9698f285e3fd03db935405473379f1c6bf86377a","published":"Fri, 19 Jun 2026 00:00:00 -0400","receipt_hash":"f4e01ed36009ac3b904af2cc9698f285e3fd03db935405473379f1c6bf86377a","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"f4e01ed36009ac3b904af2cc9698f285e3fd03db935405473379f1c6bf86377a","observed_at":"2026-06-19T04:43:39.497162Z","parent_run_hash":"942f204649bd8fb7e5f3ac68f64dc64a5a02624b49ac200c0f629f6ff3a211f3","published":"Fri, 19 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2603.04219v2 Announce Type: replace-cross \nAbstract: We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively mixing large amounts of synthetic speech with limited real recordings often leads to speaker similarity degradation during fine-tuning. To address this issue, we propose ZeSTA, a simple domain-conditioned training framework that distinguishes real and synthetic speech via a lightweight domain embedding, combined with real-data oversampling to stabilize adaptation under extremely limited target data, without modifying the base architecture. Experiments on LibriTTS and an in-house dataset with two ZS-TTS sources demonstrate that our approach improves speaker similarity over naive synthetic augmentation while preserving intelligibility and perceptual quality. Audio samples are available on our w","title":"ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis","url":"https://arxiv.org/abs/2603.04219","vendor":"arxiv_cs_ai"},"summary":"arXiv:2603.04219v2 Announce Type: replace-cross \nAbstract: We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively mixing large amounts of synthetic speech with limited real recordings often leads to speaker similarity degradation during fine-tuning. To address this issue, we propose ZeSTA, a simple domain-conditioned training framework that distinguishes real and synthetic speech via a lightweight domain embedding, combined with real-data oversampling to stabilize adaptation under extremely limited target data, without modifying the base architecture. Experiments on LibriTTS and an in-house dataset with two ZS-TTS sources demonstrate that our approach improves speaker similarity over naive synthetic augmentation while preserving intelligibility and perceptual quality. Audio samples are available on our w","title":"ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-19T04:43:39Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2603.04219"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:21cd3011d1dda3c65c1fc5c8d1f87e0b0cd73fcfd4de6ccd3a8180ddc9d52447ab74f2eba1eda0178955938d6a1f7a92b36d301caae8a462ec027b91f3697b07","signer":"crovia.substrate","subject":{"observed_at":"2026-06-19T04:43:39Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2603.04219"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"64b7e14528a8c87f14995a0ec4e41a45b01adf0c2e6c417fec19cbe3a18182b7","leaf_index":235737,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"4c06efa9233ebda6aac85bcf3d922a6bb6e52e6742f5fa055029657d5851af6f","side":"left"},{"sibling":"d8794e764d80ce60cee3b70f33ef01b14977c038fbc3499a4a26c77f1efed9f2","side":"right"},{"sibling":"8f3cfac7a82b7483ff14ea7074ff8b248a717f78293645bbef99286f3f4dcf2a","side":"right"},{"sibling":"7824a2ba29b57f74eb656e3806574b763792543ee31e5ac934128042d6c78726","side":"left"},{"sibling":"d3804b0fab1731eeb30a2eee878bec7ce7ba8ce7702faec751d3e2bf1331464d","side":"left"},{"sibling":"39f412afa28766221bce1f35a009b6692e5c927315ca493d86f4954d9ac09857","side":"right"},{"sibling":"cff664a6462d639aed9e14805d8bb57d59dd159a92997aa1da18b50dd5d6c34f","side":"left"},{"sibling":"9af7ea2b04101a414ff44ef903d5d381777f0286b489347e7e959b64158ff697","side":"left"},{"sibling":"aa68ebe8f5e8e96388fc8d1af3aa08be7ccd27ab4cebcf5913560c48d877bc27","side":"right"},{"sibling":"8253d44cf1ed30d3ab19c2b339fb4000a1fa173182c65390e9e8dabf8173b9e9","side":"right"},{"sibling":"e2bf9b60400244c698c0196109f54323457abc5b64dee08ec33ab14cc4faaef7","side":"right"},{"sibling":"86664e7f68ba08b8dfcf77dda51a4dfa7fcfc986d4ad7c704ffb71b669202da7","side":"left"},{"sibling":"410c633928fea11c5b4bdddb431956b1d7c320db9cda00d2fe32e0fcf888d7b7","side":"left"},{"sibling":"b52a771530dd1686bca49e42088898b86da94879579cd6a995c6ab0598a665fe","side":"right"},{"sibling":"a116bb92f9b0350491155b470acc86d006c33ec558759e49e56614a54c39f242","side":"right"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":241122,"merkle_root":"7a906c6a26ff6c6feabc2feaba6a1a70c515e6fd72a38c779293b0f78ff291c4","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260622T183701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-23T06:25:25Z","sig_algorithm":"ed25519","signature":"5576b1d56d5dbb0d96c780fa3ca0940d805c8de95c6251bc87297f0be058aa5e37eb53a6aa1b601381f489f093842cf674b28737ed8e46ce3a49814b5e57290c","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_e55a5060477502c65b1783b010f6a5a0f8037722c6dd9eabbf58870a6d28e530"}}