{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z3BRWJYSH7JLPAKPUSVYRH3HEQ","short_pith_number":"pith:Z3BRWJYS","schema_version":"1.0","canonical_sha256":"cec31b27123fd2b7814fa4ab889f672413924758c38509cdca349da98b2a0cb7","source":{"kind":"arxiv","id":"2401.14321","version":5},"attestation_state":"computed","paper":{"title":"VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Hankun Wang, Hui Zhang, Kai Yu, Shuai Wang, Xie Chen, Yifan Yang, Yiwei Guo, Zhikang Niu","submitted_at":"2024-01-25T17:19:01Z","abstract_excerpt":"Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt. However, such decoder-only TTS models lack monotonic alignment constraints, sometimes leading to hallucination issues such as mispronunciation, word skipping and repeating. To address this limitation, we propose VALL-T, a generative Transducer model that introduces shifting relative position embeddings for input phoneme sequence, explicitly indicating the monotonic generation process while maintain"},"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":"2401.14321","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-25T17:19:01Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3e930d122104b514e570653bf7396af60ced29886ded1e639180fcde161bba47","abstract_canon_sha256":"783206a98fc6e56ad4dc3a3467cf0849793cb15f1601684574dfa4e826a59fe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:52.712937Z","signature_b64":"T7QHn7hLsX9tfpbmCMcBU8nJNvaq429+9ueA5mBZytpynNnWnwDl5DG3ceM2ccxJSTcVkBWyU0IDGKWPLsuZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cec31b27123fd2b7814fa4ab889f672413924758c38509cdca349da98b2a0cb7","last_reissued_at":"2026-07-05T10:30:52.712108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:52.712108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Hankun Wang, Hui Zhang, Kai Yu, Shuai Wang, Xie Chen, Yifan Yang, Yiwei Guo, Zhikang Niu","submitted_at":"2024-01-25T17:19:01Z","abstract_excerpt":"Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt. However, such decoder-only TTS models lack monotonic alignment constraints, sometimes leading to hallucination issues such as mispronunciation, word skipping and repeating. To address this limitation, we propose VALL-T, a generative Transducer model that introduces shifting relative position embeddings for input phoneme sequence, explicitly indicating the monotonic generation process while maintain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14321","kind":"arxiv","version":5},"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/2401.14321/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":"2401.14321","created_at":"2026-07-05T10:30:52.712196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14321v5","created_at":"2026-07-05T10:30:52.712196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14321","created_at":"2026-07-05T10:30:52.712196+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3BRWJYSH7JL","created_at":"2026-07-05T10:30:52.712196+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3BRWJYSH7JLPAKP","created_at":"2026-07-05T10:30:52.712196+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3BRWJYS","created_at":"2026-07-05T10:30:52.712196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17589","citing_title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10117","citing_title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z3BRWJYSH7JLPAKPUSVYRH3HEQ","json":"https://pith.science/pith/Z3BRWJYSH7JLPAKPUSVYRH3HEQ.json","graph_json":"https://pith.science/api/pith-number/Z3BRWJYSH7JLPAKPUSVYRH3HEQ/graph.json","events_json":"https://pith.science/api/pith-number/Z3BRWJYSH7JLPAKPUSVYRH3HEQ/events.json","paper":"https://pith.science/paper/Z3BRWJYS"},"agent_actions":{"view_html":"https://pith.science/pith/Z3BRWJYSH7JLPAKPUSVYRH3HEQ","download_json":"https://pith.science/pith/Z3BRWJYSH7JLPAKPUSVYRH3HEQ.json","view_paper":"https://pith.science/paper/Z3BRWJYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14321&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3BRWJYSH7JLPAKPUSVYRH3HEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3BRWJYSH7JLPAKPUSVYRH3HEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3BRWJYSH7JLPAKPUSVYRH3HEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3BRWJYSH7JLPAKPUSVYRH3HEQ/action/storage_attestation","attest_author":"https://pith.science/pith/Z3BRWJYSH7JLPAKPUSVYRH3HEQ/action/author_attestation","sign_citation":"https://pith.science/pith/Z3BRWJYSH7JLPAKPUSVYRH3HEQ/action/citation_signature","submit_replication":"https://pith.science/pith/Z3BRWJYSH7JLPAKPUSVYRH3HEQ/action/replication_record"}},"created_at":"2026-07-05T10:30:52.712196+00:00","updated_at":"2026-07-05T10:30:52.712196+00:00"}