{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PZ7N7PZ2VAO63YBLP3YW4WPYNE","short_pith_number":"pith:PZ7N7PZ2","canonical_record":{"source":{"id":"2412.08112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T05:39:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"5e723f97ec09b2cb619bf99199925e56e30b7fdd1919491e99374d70b655951e","abstract_canon_sha256":"2ea14fe0b9843b616dcf71eeca02f448ae98c20e38963128423b46875ce87e8f"},"schema_version":"1.0"},"canonical_sha256":"7e7edfbf3aa81dede02b7ef16e59f869190ab1ed02fda4a00571b2a7edca10f0","source":{"kind":"arxiv","id":"2412.08112","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08112","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08112v1","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08112","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"PZ7N7PZ2VAO6","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_16","alias_value":"PZ7N7PZ2VAO63YBL","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_8","alias_value":"PZ7N7PZ2","created_at":"2026-07-05T09:47:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PZ7N7PZ2VAO63YBLP3YW4WPYNE","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T05:39:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"5e723f97ec09b2cb619bf99199925e56e30b7fdd1919491e99374d70b655951e","abstract_canon_sha256":"2ea14fe0b9843b616dcf71eeca02f448ae98c20e38963128423b46875ce87e8f"},"schema_version":"1.0"},"canonical_sha256":"7e7edfbf3aa81dede02b7ef16e59f869190ab1ed02fda4a00571b2a7edca10f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:44.646718Z","signature_b64":"N7gzv2A2n3ZEY9a7n0vxgj3qjhyL79g0Ur0FlHVf2ifZ1LxLX5ebOI61eiB0LdfmV94lWA7AsvdSjR3mo4ZOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e7edfbf3aa81dede02b7ef16e59f869190ab1ed02fda4a00571b2a7edca10f0","last_reissued_at":"2026-07-05T09:47:44.646285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:44.646285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08112","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jl4TlQ3u+sduiyqf0u/Q5Bv1DKI1S+1HvN0XORLMWr+fWg9eA+Jw52ANUfkPs+pwcFPu87AIpCEL1Ye0bcEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:08:11.178918Z"},"content_sha256":"b133d9cd43def7805b7d268d428376c78a773b76e2fd34ec8d331c6d5fd3b032","schema_version":"1.0","event_id":"sha256:b133d9cd43def7805b7d268d428376c78a773b76e2fd34ec8d331c6d5fd3b032"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PZ7N7PZ2VAO63YBLP3YW4WPYNE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligner-Guided Training Paradigm: Advancing Text-to-Speech Models with Aligner Guided Duration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haowei Lou, Helen Paik, Lina Yao, Wen Hu","submitted_at":"2024-12-11T05:39:12Z","abstract_excerpt":"Recent advancements in text-to-speech (TTS) systems, such as FastSpeech and StyleSpeech, have significantly improved speech generation quality. However, these models often rely on duration generated by external tools like the Montreal Forced Aligner, which can be time-consuming and lack flexibility. The importance of accurate duration is often underestimated, despite their crucial role in achieving natural prosody and intelligibility. To address these limitations, we propose a novel Aligner-Guided Training Paradigm that prioritizes accurate duration labelling by training an aligner before the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08112","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/2412.08112/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vHuokwaZ2XlVPyYhsTfWJQRNGVdUaWCdVtAh3r2WaIglrAnoMOYx5Zrd293/gNIxak2OyJRcK0xg7V7IhLVuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:08:11.179440Z"},"content_sha256":"53ecf0610cc41b189eabc2d78dc3848f9d7bea0a27cc072114f5db2de5b918ae","schema_version":"1.0","event_id":"sha256:53ecf0610cc41b189eabc2d78dc3848f9d7bea0a27cc072114f5db2de5b918ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZ7N7PZ2VAO63YBLP3YW4WPYNE/bundle.json","state_url":"https://pith.science/pith/PZ7N7PZ2VAO63YBLP3YW4WPYNE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZ7N7PZ2VAO63YBLP3YW4WPYNE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T07:08:11Z","links":{"resolver":"https://pith.science/pith/PZ7N7PZ2VAO63YBLP3YW4WPYNE","bundle":"https://pith.science/pith/PZ7N7PZ2VAO63YBLP3YW4WPYNE/bundle.json","state":"https://pith.science/pith/PZ7N7PZ2VAO63YBLP3YW4WPYNE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZ7N7PZ2VAO63YBLP3YW4WPYNE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PZ7N7PZ2VAO63YBLP3YW4WPYNE","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":"2ea14fe0b9843b616dcf71eeca02f448ae98c20e38963128423b46875ce87e8f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T05:39:12Z","title_canon_sha256":"5e723f97ec09b2cb619bf99199925e56e30b7fdd1919491e99374d70b655951e"},"schema_version":"1.0","source":{"id":"2412.08112","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08112","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08112v1","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08112","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"PZ7N7PZ2VAO6","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_16","alias_value":"PZ7N7PZ2VAO63YBL","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_8","alias_value":"PZ7N7PZ2","created_at":"2026-07-05T09:47:44Z"}],"graph_snapshots":[{"event_id":"sha256:53ecf0610cc41b189eabc2d78dc3848f9d7bea0a27cc072114f5db2de5b918ae","target":"graph","created_at":"2026-07-05T09:47:44Z","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/2412.08112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in text-to-speech (TTS) systems, such as FastSpeech and StyleSpeech, have significantly improved speech generation quality. However, these models often rely on duration generated by external tools like the Montreal Forced Aligner, which can be time-consuming and lack flexibility. The importance of accurate duration is often underestimated, despite their crucial role in achieving natural prosody and intelligibility. To address these limitations, we propose a novel Aligner-Guided Training Paradigm that prioritizes accurate duration labelling by training an aligner before the ","authors_text":"Haowei Lou, Helen Paik, Lina Yao, Wen Hu","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T05:39:12Z","title":"Aligner-Guided Training Paradigm: Advancing Text-to-Speech Models with Aligner Guided Duration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08112","kind":"arxiv","version":1},"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:b133d9cd43def7805b7d268d428376c78a773b76e2fd34ec8d331c6d5fd3b032","target":"record","created_at":"2026-07-05T09:47:44Z","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":"2ea14fe0b9843b616dcf71eeca02f448ae98c20e38963128423b46875ce87e8f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T05:39:12Z","title_canon_sha256":"5e723f97ec09b2cb619bf99199925e56e30b7fdd1919491e99374d70b655951e"},"schema_version":"1.0","source":{"id":"2412.08112","kind":"arxiv","version":1}},"canonical_sha256":"7e7edfbf3aa81dede02b7ef16e59f869190ab1ed02fda4a00571b2a7edca10f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e7edfbf3aa81dede02b7ef16e59f869190ab1ed02fda4a00571b2a7edca10f0","first_computed_at":"2026-07-05T09:47:44.646285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:44.646285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N7gzv2A2n3ZEY9a7n0vxgj3qjhyL79g0Ur0FlHVf2ifZ1LxLX5ebOI61eiB0LdfmV94lWA7AsvdSjR3mo4ZOBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:44.646718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08112","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b133d9cd43def7805b7d268d428376c78a773b76e2fd34ec8d331c6d5fd3b032","sha256:53ecf0610cc41b189eabc2d78dc3848f9d7bea0a27cc072114f5db2de5b918ae"],"state_sha256":"5c7529f3569ab646068f84599dcadf18abe2b751547dc09b9900ca55d56fb0bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wI5+BnG8ByApDz+beBpJ9yZ+FFpmoF8U6QB2ol9McWPt+iekevwZ/+y5kAuJXwHN4MFwzWhYC247O7cfAjkvDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:08:11.186118Z","bundle_sha256":"73453f236de5847f771e85fc292776adcac174a104dac2af226b249f378aac82"}}