{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:D2RHIK5XCLWPR2QM4FBOBRJRIS","short_pith_number":"pith:D2RHIK5X","schema_version":"1.0","canonical_sha256":"1ea2742bb712ecf8ea0ce142e0c531448e96a03c048cb560307eb0910e67a413","source":{"kind":"arxiv","id":"2203.11049","version":2},"attestation_state":"computed","paper":{"title":"AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bac Nguyen, Fabien Cardinaux, Stefan Uhlich","submitted_at":"2022-03-21T15:14:44Z","abstract_excerpt":"Parallel text-to-speech (TTS) models have recently enabled fast and highly-natural speech synthesis. However, they typically require external alignment models, which are not necessarily optimized for the decoder as they are not jointly trained. In this paper, we propose a differentiable duration method for learning monotonic alignments between input and output sequences. Our method is based on a soft-duration mechanism that optimizes a stochastic process in expectation. Using this differentiable duration method, we introduce AutoTTS, a direct text-to-waveform speech synthesis model. AutoTTS en"},"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":"2203.11049","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-21T15:14:44Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"5c56f4680b002c0682b577b3b3ef1bce8d6586c99207079c2c9af7e602214847","abstract_canon_sha256":"ccbd712e553ef1ca6ae866ed428e7704d6e8b4bd2c2803a77fa6711033fe201d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:32.879810Z","signature_b64":"WTMN4lYif/LF6kf6mLhAKago6LRGSyACR75bl2r5W4p4sKntxeckFW/iTlP6Vk6BM78RPkJHhHOtKR7J56W6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ea2742bb712ecf8ea0ce142e0c531448e96a03c048cb560307eb0910e67a413","last_reissued_at":"2026-07-05T05:48:32.879428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:32.879428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bac Nguyen, Fabien Cardinaux, Stefan Uhlich","submitted_at":"2022-03-21T15:14:44Z","abstract_excerpt":"Parallel text-to-speech (TTS) models have recently enabled fast and highly-natural speech synthesis. However, they typically require external alignment models, which are not necessarily optimized for the decoder as they are not jointly trained. In this paper, we propose a differentiable duration method for learning monotonic alignments between input and output sequences. Our method is based on a soft-duration mechanism that optimizes a stochastic process in expectation. Using this differentiable duration method, we introduce AutoTTS, a direct text-to-waveform speech synthesis model. AutoTTS en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11049","kind":"arxiv","version":2},"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/2203.11049/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":"2203.11049","created_at":"2026-07-05T05:48:32.879484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11049v2","created_at":"2026-07-05T05:48:32.879484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11049","created_at":"2026-07-05T05:48:32.879484+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2RHIK5XCLWP","created_at":"2026-07-05T05:48:32.879484+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2RHIK5XCLWPR2QM","created_at":"2026-07-05T05:48:32.879484+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2RHIK5X","created_at":"2026-07-05T05:48:32.879484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2RHIK5XCLWPR2QM4FBOBRJRIS","json":"https://pith.science/pith/D2RHIK5XCLWPR2QM4FBOBRJRIS.json","graph_json":"https://pith.science/api/pith-number/D2RHIK5XCLWPR2QM4FBOBRJRIS/graph.json","events_json":"https://pith.science/api/pith-number/D2RHIK5XCLWPR2QM4FBOBRJRIS/events.json","paper":"https://pith.science/paper/D2RHIK5X"},"agent_actions":{"view_html":"https://pith.science/pith/D2RHIK5XCLWPR2QM4FBOBRJRIS","download_json":"https://pith.science/pith/D2RHIK5XCLWPR2QM4FBOBRJRIS.json","view_paper":"https://pith.science/paper/D2RHIK5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11049&json=true","fetch_graph":"https://pith.science/api/pith-number/D2RHIK5XCLWPR2QM4FBOBRJRIS/graph.json","fetch_events":"https://pith.science/api/pith-number/D2RHIK5XCLWPR2QM4FBOBRJRIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2RHIK5XCLWPR2QM4FBOBRJRIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2RHIK5XCLWPR2QM4FBOBRJRIS/action/storage_attestation","attest_author":"https://pith.science/pith/D2RHIK5XCLWPR2QM4FBOBRJRIS/action/author_attestation","sign_citation":"https://pith.science/pith/D2RHIK5XCLWPR2QM4FBOBRJRIS/action/citation_signature","submit_replication":"https://pith.science/pith/D2RHIK5XCLWPR2QM4FBOBRJRIS/action/replication_record"}},"created_at":"2026-07-05T05:48:32.879484+00:00","updated_at":"2026-07-05T05:48:32.879484+00:00"}