{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TAGCTIWO3MVWIQY5H2XLQM6NGC","short_pith_number":"pith:TAGCTIWO","canonical_record":{"source":{"id":"2505.19595","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T07:07:16Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6a367b3b6b7b16ad507d9887cc002e2a31a5de527acb4edbe5e10181a061dc98","abstract_canon_sha256":"6791fa01c537a0ce11382f5c6c95930865e44e2984d1c98c07c98ca0892ecb69"},"schema_version":"1.0"},"canonical_sha256":"980c29a2cedb2b64431d3eaeb833cd30b4d8c979b37211d9531679a81bd542e2","source":{"kind":"arxiv","id":"2505.19595","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19595","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19595v2","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19595","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"pith_short_12","alias_value":"TAGCTIWO3MVW","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"pith_short_16","alias_value":"TAGCTIWO3MVWIQY5","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"pith_short_8","alias_value":"TAGCTIWO","created_at":"2026-07-05T11:12:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TAGCTIWO3MVWIQY5H2XLQM6NGC","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19595","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T07:07:16Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6a367b3b6b7b16ad507d9887cc002e2a31a5de527acb4edbe5e10181a061dc98","abstract_canon_sha256":"6791fa01c537a0ce11382f5c6c95930865e44e2984d1c98c07c98ca0892ecb69"},"schema_version":"1.0"},"canonical_sha256":"980c29a2cedb2b64431d3eaeb833cd30b4d8c979b37211d9531679a81bd542e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:33.512147Z","signature_b64":"Vt5aevENMJ4luky7rQHUksXq5tlOX+ErkPeSxaCtDRf1vZXv1BE5TpWhWtHuPKtjmC+F176SI65+8BK3CUpDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"980c29a2cedb2b64431d3eaeb833cd30b4d8c979b37211d9531679a81bd542e2","last_reissued_at":"2026-07-05T11:12:33.511597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:33.511597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19595","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"34k4CdXHNunAwCaBZYGggOkyDAz6e+FyOPd02iCdmvpE1xJIEeRmbMS/jn34rTH0GKLVYmHri4bkYKWzOlKMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:14:36.247520Z"},"content_sha256":"f08b726955aa628a2ba93d78aaedec9f716bed64f35a43ff987446521819fcf5","schema_version":"1.0","event_id":"sha256:f08b726955aa628a2ba93d78aaedec9f716bed64f35a43ff987446521819fcf5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TAGCTIWO3MVWIQY5H2XLQM6NGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunhui Wang, Jeongsoo Choi, Ji-Hoon Kim, Joon Son Chung, Xie Chen, Zhikang Niu","submitted_at":"2025-05-26T07:07:16Z","abstract_excerpt":"The goal of this paper is to optimize the training process of diffusion-based text-to-speech models. While recent studies have achieved remarkable advancements, their training demands substantial time and computational costs, largely due to the implicit guidance of diffusion models in learning complex intermediate representations. To address this, we propose A-DMA, an effective strategy for Accelerating training with Dual Modality Alignment. Our method introduces a novel alignment pipeline leveraging both text and speech modalities: text-guided alignment, which incorporates contextual represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19595","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/2505.19595/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":"2026-07-05T11:12:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tqa/mU2oD0nGjrR9I40tFGsQJ5cNx9c5qQxdBN+iufrkM+aZydyftTdbUs1lwvh+zbzezd4zS4zdWKWbmUBSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:14:36.248012Z"},"content_sha256":"f9e4ad9cd3afb8195af74ee5eaa4ff93b04cb7717ac0dc3878beb8668dd71ac0","schema_version":"1.0","event_id":"sha256:f9e4ad9cd3afb8195af74ee5eaa4ff93b04cb7717ac0dc3878beb8668dd71ac0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TAGCTIWO3MVWIQY5H2XLQM6NGC/bundle.json","state_url":"https://pith.science/pith/TAGCTIWO3MVWIQY5H2XLQM6NGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TAGCTIWO3MVWIQY5H2XLQM6NGC/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":"2026-08-06T15:14:36Z","links":{"resolver":"https://pith.science/pith/TAGCTIWO3MVWIQY5H2XLQM6NGC","bundle":"https://pith.science/pith/TAGCTIWO3MVWIQY5H2XLQM6NGC/bundle.json","state":"https://pith.science/pith/TAGCTIWO3MVWIQY5H2XLQM6NGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TAGCTIWO3MVWIQY5H2XLQM6NGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TAGCTIWO3MVWIQY5H2XLQM6NGC","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":"6791fa01c537a0ce11382f5c6c95930865e44e2984d1c98c07c98ca0892ecb69","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T07:07:16Z","title_canon_sha256":"6a367b3b6b7b16ad507d9887cc002e2a31a5de527acb4edbe5e10181a061dc98"},"schema_version":"1.0","source":{"id":"2505.19595","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19595","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19595v2","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19595","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"pith_short_12","alias_value":"TAGCTIWO3MVW","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"pith_short_16","alias_value":"TAGCTIWO3MVWIQY5","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"pith_short_8","alias_value":"TAGCTIWO","created_at":"2026-07-05T11:12:33Z"}],"graph_snapshots":[{"event_id":"sha256:f9e4ad9cd3afb8195af74ee5eaa4ff93b04cb7717ac0dc3878beb8668dd71ac0","target":"graph","created_at":"2026-07-05T11:12:33Z","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/2505.19595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this paper is to optimize the training process of diffusion-based text-to-speech models. While recent studies have achieved remarkable advancements, their training demands substantial time and computational costs, largely due to the implicit guidance of diffusion models in learning complex intermediate representations. To address this, we propose A-DMA, an effective strategy for Accelerating training with Dual Modality Alignment. Our method introduces a novel alignment pipeline leveraging both text and speech modalities: text-guided alignment, which incorporates contextual represen","authors_text":"Chunhui Wang, Jeongsoo Choi, Ji-Hoon Kim, Joon Son Chung, Xie Chen, Zhikang Niu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T07:07:16Z","title":"Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19595","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:f08b726955aa628a2ba93d78aaedec9f716bed64f35a43ff987446521819fcf5","target":"record","created_at":"2026-07-05T11:12:33Z","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":"6791fa01c537a0ce11382f5c6c95930865e44e2984d1c98c07c98ca0892ecb69","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T07:07:16Z","title_canon_sha256":"6a367b3b6b7b16ad507d9887cc002e2a31a5de527acb4edbe5e10181a061dc98"},"schema_version":"1.0","source":{"id":"2505.19595","kind":"arxiv","version":2}},"canonical_sha256":"980c29a2cedb2b64431d3eaeb833cd30b4d8c979b37211d9531679a81bd542e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"980c29a2cedb2b64431d3eaeb833cd30b4d8c979b37211d9531679a81bd542e2","first_computed_at":"2026-07-05T11:12:33.511597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:33.511597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vt5aevENMJ4luky7rQHUksXq5tlOX+ErkPeSxaCtDRf1vZXv1BE5TpWhWtHuPKtjmC+F176SI65+8BK3CUpDBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:33.512147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19595","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f08b726955aa628a2ba93d78aaedec9f716bed64f35a43ff987446521819fcf5","sha256:f9e4ad9cd3afb8195af74ee5eaa4ff93b04cb7717ac0dc3878beb8668dd71ac0"],"state_sha256":"735e5890495340f7e9ef3a1d23cdcd0af0fc11bbcd3324121118dff7a5fa76e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a21/lyP3Dec44JfUk8eyzbHipVC9T/w8nbAyqtG6Pr1hyqSE+kmoTMr52P2S7JaRjKb2gcZ9g1YXMdboufVcCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:14:36.251563Z","bundle_sha256":"8408004ca5c5093f898ead964b381d62c29afd062579fced9ad38116c1bd63df"}}