{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VF5Q2OOX7JO6IVHWMLM24BASYL","short_pith_number":"pith:VF5Q2OOX","schema_version":"1.0","canonical_sha256":"a97b0d39d7fa5de454f662d9ae0412c2c3f36f7599222dfbf64384b27cb65a53","source":{"kind":"arxiv","id":"2207.06088","version":1},"attestation_state":"computed","paper":{"title":"Controllable and Lossless Non-Autoregressive End-to-End Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxu Hu, Hang Zhao, Menglin Wu, Qiao Tian, Xudong Liu, Yuping Wang, Yuxuan Wang, Zhengxi Liu","submitted_at":"2022-07-13T09:57:06Z","abstract_excerpt":"Some recent studies have demonstrated the feasibility of single-stage neural text-to-speech, which does not need to generate mel-spectrograms but generates the raw waveforms directly from the text. Single-stage text-to-speech often faces two problems: a) the one-to-many mapping problem due to multiple speech variations and b) insufficiency of high frequency reconstruction due to the lack of supervision of ground-truth acoustic features during training. To solve the a) problem and generate more expressive speech, we propose a novel phoneme-level prosody modeling method based on a variational au"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2207.06088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T09:57:06Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f1bb7e25938b779fc31ca30755edb7dd763f43ca4ed09460ef6902aef253c17c","abstract_canon_sha256":"2341ed52d64af83da10aa925eadbb57e882acdda4a6b40b9f97e8bcd1cd5c5f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:54.438260Z","signature_b64":"jM1pwkoynpid1OdYPNFjkrt9ZBOB9f4rMQPLfel1Qc+cF6uryku8CdHnIK7aE2ZTeOQptYnnMu0oU9ohy7j/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a97b0d39d7fa5de454f662d9ae0412c2c3f36f7599222dfbf64384b27cb65a53","last_reissued_at":"2026-07-05T04:39:54.437782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:54.437782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable and Lossless Non-Autoregressive End-to-End Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxu Hu, Hang Zhao, Menglin Wu, Qiao Tian, Xudong Liu, Yuping Wang, Yuxuan Wang, Zhengxi Liu","submitted_at":"2022-07-13T09:57:06Z","abstract_excerpt":"Some recent studies have demonstrated the feasibility of single-stage neural text-to-speech, which does not need to generate mel-spectrograms but generates the raw waveforms directly from the text. Single-stage text-to-speech often faces two problems: a) the one-to-many mapping problem due to multiple speech variations and b) insufficiency of high frequency reconstruction due to the lack of supervision of ground-truth acoustic features during training. To solve the a) problem and generate more expressive speech, we propose a novel phoneme-level prosody modeling method based on a variational au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06088","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2207.06088/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2207.06088","created_at":"2026-07-05T04:39:54.437839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.06088v1","created_at":"2026-07-05T04:39:54.437839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06088","created_at":"2026-07-05T04:39:54.437839+00:00"},{"alias_kind":"pith_short_12","alias_value":"VF5Q2OOX7JO6","created_at":"2026-07-05T04:39:54.437839+00:00"},{"alias_kind":"pith_short_16","alias_value":"VF5Q2OOX7JO6IVHW","created_at":"2026-07-05T04:39:54.437839+00:00"},{"alias_kind":"pith_short_8","alias_value":"VF5Q2OOX","created_at":"2026-07-05T04:39:54.437839+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.02430","citing_title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VF5Q2OOX7JO6IVHWMLM24BASYL","json":"https://pith.science/pith/VF5Q2OOX7JO6IVHWMLM24BASYL.json","graph_json":"https://pith.science/api/pith-number/VF5Q2OOX7JO6IVHWMLM24BASYL/graph.json","events_json":"https://pith.science/api/pith-number/VF5Q2OOX7JO6IVHWMLM24BASYL/events.json","paper":"https://pith.science/paper/VF5Q2OOX"},"agent_actions":{"view_html":"https://pith.science/pith/VF5Q2OOX7JO6IVHWMLM24BASYL","download_json":"https://pith.science/pith/VF5Q2OOX7JO6IVHWMLM24BASYL.json","view_paper":"https://pith.science/paper/VF5Q2OOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.06088&json=true","fetch_graph":"https://pith.science/api/pith-number/VF5Q2OOX7JO6IVHWMLM24BASYL/graph.json","fetch_events":"https://pith.science/api/pith-number/VF5Q2OOX7JO6IVHWMLM24BASYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VF5Q2OOX7JO6IVHWMLM24BASYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VF5Q2OOX7JO6IVHWMLM24BASYL/action/storage_attestation","attest_author":"https://pith.science/pith/VF5Q2OOX7JO6IVHWMLM24BASYL/action/author_attestation","sign_citation":"https://pith.science/pith/VF5Q2OOX7JO6IVHWMLM24BASYL/action/citation_signature","submit_replication":"https://pith.science/pith/VF5Q2OOX7JO6IVHWMLM24BASYL/action/replication_record"}},"created_at":"2026-07-05T04:39:54.437839+00:00","updated_at":"2026-07-05T04:39:54.437839+00:00"}