{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7BFNWOBBWD73UFV22MI5PVYQUP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4b1bf77625532e35a1de54e9014299da45de45641c66c3e53d07fcfede3f055e","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-30T17:17:07Z","title_canon_sha256":"73d383b5de3a5fcdca8e977837e11e79fac1958c02b8149cef9ba2599ca17a10"},"schema_version":"1.0","source":{"id":"2404.19723","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19723","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19723v2","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19723","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"7BFNWOBBWD73","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"7BFNWOBBWD73UFV2","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"7BFNWOBB","created_at":"2026-07-05T09:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:814770c4909a8b9809fdd40d2417ca7a912c8c636f07f47dc5778948c3170e4a","target":"graph","created_at":"2026-07-05T09:22:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.19723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent popular decoder-only text-to-speech models are known for their ability of generating natural-sounding speech. However, such models sometimes suffer from word skipping and repeating due to the lack of explicit monotonic alignment constraints. In this paper, we notice from the attention maps that some particular attention heads of the decoder-only model indicate the alignments between speech and text. We call the attention maps of those heads Alignment-Emerged Attention Maps (AEAMs). Based on this discovery, we propose a novel inference method without altering the training process, named ","authors_text":"Chenpeng Du, Hankun Wang, Kai Yu, Shuai Wang, Xie Chen, Yiwei Guo","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-30T17:17:07Z","title":"Attention-Constrained Inference for Robust Decoder-Only Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19723","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4cbe48efa3a223b3aeb80bcb080d71b42a2a4a23a3a108e01366a533d1a38249","target":"record","created_at":"2026-07-05T09:22:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4b1bf77625532e35a1de54e9014299da45de45641c66c3e53d07fcfede3f055e","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-30T17:17:07Z","title_canon_sha256":"73d383b5de3a5fcdca8e977837e11e79fac1958c02b8149cef9ba2599ca17a10"},"schema_version":"1.0","source":{"id":"2404.19723","kind":"arxiv","version":2}},"canonical_sha256":"f84adb3821b0ffba16bad311d7d710a3f7af1dd4776c3fd9b926bb4b00a65c5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f84adb3821b0ffba16bad311d7d710a3f7af1dd4776c3fd9b926bb4b00a65c5d","first_computed_at":"2026-07-05T09:22:17.726720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:17.726720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8uhHLP3u8FMLkqacY/xlV5RKhUZubr2/9htHukUfpQEcod4s+t664Xs/F/2QkmlFRg96EeYfHFNi2mz7s88jDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:17.727177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.19723","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cbe48efa3a223b3aeb80bcb080d71b42a2a4a23a3a108e01366a533d1a38249","sha256:814770c4909a8b9809fdd40d2417ca7a912c8c636f07f47dc5778948c3170e4a"],"state_sha256":"714aa94e27f01663b7ae9c8a16ec00868932a8d104a510c9dec844ea6a324bce"}