{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MRIFHQDGBSRMXC7MR5YPSYKHJO","short_pith_number":"pith:MRIFHQDG","schema_version":"1.0","canonical_sha256":"645053c0660ca2cb8bec8f70f961474baef4c00c2330138e4d3eb849c29a1430","source":{"kind":"arxiv","id":"2106.02830","version":1},"attestation_state":"computed","paper":{"title":"Reinforce-Aligner: Reinforcement Alignment Search for Robust End-to-End Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hyunseung Chung, Sang-Hoon Lee, Seong-Whan Lee","submitted_at":"2021-06-05T08:08:37Z","abstract_excerpt":"Text-to-speech (TTS) synthesis is the process of producing synthesized speech from text or phoneme input. Traditional TTS models contain multiple processing steps and require external aligners, which provide attention alignments of phoneme-to-frame sequences. As the complexity increases and efficiency decreases with every additional step, there is expanding demand in modern synthesis pipelines for end-to-end TTS with efficient internal aligners. In this work, we propose an end-to-end text-to-waveform network with a novel reinforcement learning based duration search method. Our proposed generat"},"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":"2106.02830","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-05T08:08:37Z","cross_cats_sorted":[],"title_canon_sha256":"434b70247594b7ee411a9655a411e4445dd939e97c1a8d967aeae89484df05b7","abstract_canon_sha256":"7894ac25c2d7dabdc02a72c4f43e02b9b024e875c0d93c0c9de31da64e4a9a45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:30.636953Z","signature_b64":"N6M9etjWfk3dFyk9VHF++ba7FN5yZZlgqdGXKvxl5mD3j6vM9NHLmnnSl+QeOmqMVHpPNIZc0H6fEAD/9N3kAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"645053c0660ca2cb8bec8f70f961474baef4c00c2330138e4d3eb849c29a1430","last_reissued_at":"2026-07-05T02:46:30.636474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:30.636474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforce-Aligner: Reinforcement Alignment Search for Robust End-to-End Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hyunseung Chung, Sang-Hoon Lee, Seong-Whan Lee","submitted_at":"2021-06-05T08:08:37Z","abstract_excerpt":"Text-to-speech (TTS) synthesis is the process of producing synthesized speech from text or phoneme input. Traditional TTS models contain multiple processing steps and require external aligners, which provide attention alignments of phoneme-to-frame sequences. As the complexity increases and efficiency decreases with every additional step, there is expanding demand in modern synthesis pipelines for end-to-end TTS with efficient internal aligners. In this work, we propose an end-to-end text-to-waveform network with a novel reinforcement learning based duration search method. Our proposed generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02830","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/2106.02830/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":"2106.02830","created_at":"2026-07-05T02:46:30.636532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.02830v1","created_at":"2026-07-05T02:46:30.636532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02830","created_at":"2026-07-05T02:46:30.636532+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRIFHQDGBSRM","created_at":"2026-07-05T02:46:30.636532+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRIFHQDGBSRMXC7M","created_at":"2026-07-05T02:46:30.636532+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRIFHQDG","created_at":"2026-07-05T02:46:30.636532+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/MRIFHQDGBSRMXC7MR5YPSYKHJO","json":"https://pith.science/pith/MRIFHQDGBSRMXC7MR5YPSYKHJO.json","graph_json":"https://pith.science/api/pith-number/MRIFHQDGBSRMXC7MR5YPSYKHJO/graph.json","events_json":"https://pith.science/api/pith-number/MRIFHQDGBSRMXC7MR5YPSYKHJO/events.json","paper":"https://pith.science/paper/MRIFHQDG"},"agent_actions":{"view_html":"https://pith.science/pith/MRIFHQDGBSRMXC7MR5YPSYKHJO","download_json":"https://pith.science/pith/MRIFHQDGBSRMXC7MR5YPSYKHJO.json","view_paper":"https://pith.science/paper/MRIFHQDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.02830&json=true","fetch_graph":"https://pith.science/api/pith-number/MRIFHQDGBSRMXC7MR5YPSYKHJO/graph.json","fetch_events":"https://pith.science/api/pith-number/MRIFHQDGBSRMXC7MR5YPSYKHJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRIFHQDGBSRMXC7MR5YPSYKHJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRIFHQDGBSRMXC7MR5YPSYKHJO/action/storage_attestation","attest_author":"https://pith.science/pith/MRIFHQDGBSRMXC7MR5YPSYKHJO/action/author_attestation","sign_citation":"https://pith.science/pith/MRIFHQDGBSRMXC7MR5YPSYKHJO/action/citation_signature","submit_replication":"https://pith.science/pith/MRIFHQDGBSRMXC7MR5YPSYKHJO/action/replication_record"}},"created_at":"2026-07-05T02:46:30.636532+00:00","updated_at":"2026-07-05T02:46:30.636532+00:00"}