{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6G62EC4XGU3B6ZFGWFI5K44BIH","short_pith_number":"pith:6G62EC4X","canonical_record":{"source":{"id":"2406.04281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T17:27:09Z","cross_cats_sorted":[],"title_canon_sha256":"e6e650257bacc8c47660b0b7200ab7b251723683e0cd275f063e48cfb13c4479","abstract_canon_sha256":"2c0001dd4f536f6e09f0521defe6441a3a935f4928eeca047d0d00140e0d882e"},"schema_version":"1.0"},"canonical_sha256":"f1bda20b9735361f64a6b151d5738141e830e0fc6c222987817bfa07b0233501","source":{"kind":"arxiv","id":"2406.04281","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04281","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04281v1","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04281","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"6G62EC4XGU3B","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"6G62EC4XGU3B6ZFG","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"6G62EC4X","created_at":"2026-07-05T08:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6G62EC4XGU3B6ZFGWFI5K44BIH","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T17:27:09Z","cross_cats_sorted":[],"title_canon_sha256":"e6e650257bacc8c47660b0b7200ab7b251723683e0cd275f063e48cfb13c4479","abstract_canon_sha256":"2c0001dd4f536f6e09f0521defe6441a3a935f4928eeca047d0d00140e0d882e"},"schema_version":"1.0"},"canonical_sha256":"f1bda20b9735361f64a6b151d5738141e830e0fc6c222987817bfa07b0233501","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:28.924040Z","signature_b64":"EgXMe8XHsKhamWaH2ReAj71nNvLEox7vj2u11r9ExKYvTnAuo3Ptbrqs3QAIMaVe9ULUkxJ4t/HAUkpmG/87DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1bda20b9735361f64a6b151d5738141e830e0fc6c222987817bfa07b0233501","last_reissued_at":"2026-07-05T08:28:28.923616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:28.923616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04281","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":"2026-07-05T08:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AZ9ULCaVCaQZ8yxA0bUAHaGdWLvpjllbtNgjDEBkNC6WszwYiTWoqCxyptGg1WZKe8nFsSfTwqCV7bDKpPriAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:44:35.390082Z"},"content_sha256":"d65d1a1a54ab5373b87899895d6018097b19c39db569b52f7284ad0d59501401","schema_version":"1.0","event_id":"sha256:d65d1a1a54ab5373b87899895d6018097b19c39db569b52f7284ad0d59501401"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6G62EC4XGU3B6ZFGWFI5K44BIH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Total-Duration-Aware Duration Modeling for Text-to-Speech Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Canrun Li, Chung-Hsien Tsai, Hemin Yang, Jinyu Li, Manthan Thakker, Min Tang, Naoyuki Kanda, Sefik Emre Eskimez, Sheng Zhao, Xiaofei Wang, Zhen Xiao, Zirun Zhu","submitted_at":"2024-06-06T17:27:09Z","abstract_excerpt":"Accurate control of the total duration of generated speech by adjusting the speech rate is crucial for various text-to-speech (TTS) applications. However, the impact of adjusting the speech rate on speech quality, such as intelligibility and speaker characteristics, has been underexplored. In this work, we propose a novel total-duration-aware (TDA) duration model for TTS, where phoneme durations are predicted not only from the text input but also from an additional input of the total target duration. We also propose a MaskGIT-based duration model that enhances the diversity and quality of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04281","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/2406.04281/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":"2026-07-05T08:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+ACraVQq/skLOGWzD50Q7dDVQaEvXpfXQtX+5UU38VPlKbZB2pVFfOmhLtTQSXCHmuXXZl1ZvlVT5jPUTxGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:44:35.390740Z"},"content_sha256":"586fd317ba0af12e0bf932a0d8756c92c49094d05389262ed90e817edf482e70","schema_version":"1.0","event_id":"sha256:586fd317ba0af12e0bf932a0d8756c92c49094d05389262ed90e817edf482e70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6G62EC4XGU3B6ZFGWFI5K44BIH/bundle.json","state_url":"https://pith.science/pith/6G62EC4XGU3B6ZFGWFI5K44BIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6G62EC4XGU3B6ZFGWFI5K44BIH/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":"2026-08-15T23:44:35Z","links":{"resolver":"https://pith.science/pith/6G62EC4XGU3B6ZFGWFI5K44BIH","bundle":"https://pith.science/pith/6G62EC4XGU3B6ZFGWFI5K44BIH/bundle.json","state":"https://pith.science/pith/6G62EC4XGU3B6ZFGWFI5K44BIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6G62EC4XGU3B6ZFGWFI5K44BIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6G62EC4XGU3B6ZFGWFI5K44BIH","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":"2c0001dd4f536f6e09f0521defe6441a3a935f4928eeca047d0d00140e0d882e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T17:27:09Z","title_canon_sha256":"e6e650257bacc8c47660b0b7200ab7b251723683e0cd275f063e48cfb13c4479"},"schema_version":"1.0","source":{"id":"2406.04281","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04281","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04281v1","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04281","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"6G62EC4XGU3B","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"6G62EC4XGU3B6ZFG","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"6G62EC4X","created_at":"2026-07-05T08:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:586fd317ba0af12e0bf932a0d8756c92c49094d05389262ed90e817edf482e70","target":"graph","created_at":"2026-07-05T08:28:28Z","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/2406.04281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate control of the total duration of generated speech by adjusting the speech rate is crucial for various text-to-speech (TTS) applications. However, the impact of adjusting the speech rate on speech quality, such as intelligibility and speaker characteristics, has been underexplored. In this work, we propose a novel total-duration-aware (TDA) duration model for TTS, where phoneme durations are predicted not only from the text input but also from an additional input of the total target duration. We also propose a MaskGIT-based duration model that enhances the diversity and quality of the ","authors_text":"Canrun Li, Chung-Hsien Tsai, Hemin Yang, Jinyu Li, Manthan Thakker, Min Tang, Naoyuki Kanda, Sefik Emre Eskimez, Sheng Zhao, Xiaofei Wang, Zhen Xiao, Zirun Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T17:27:09Z","title":"Total-Duration-Aware Duration Modeling for Text-to-Speech Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04281","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:d65d1a1a54ab5373b87899895d6018097b19c39db569b52f7284ad0d59501401","target":"record","created_at":"2026-07-05T08:28:28Z","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":"2c0001dd4f536f6e09f0521defe6441a3a935f4928eeca047d0d00140e0d882e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T17:27:09Z","title_canon_sha256":"e6e650257bacc8c47660b0b7200ab7b251723683e0cd275f063e48cfb13c4479"},"schema_version":"1.0","source":{"id":"2406.04281","kind":"arxiv","version":1}},"canonical_sha256":"f1bda20b9735361f64a6b151d5738141e830e0fc6c222987817bfa07b0233501","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1bda20b9735361f64a6b151d5738141e830e0fc6c222987817bfa07b0233501","first_computed_at":"2026-07-05T08:28:28.923616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:28.923616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EgXMe8XHsKhamWaH2ReAj71nNvLEox7vj2u11r9ExKYvTnAuo3Ptbrqs3QAIMaVe9ULUkxJ4t/HAUkpmG/87DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:28.924040Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04281","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d65d1a1a54ab5373b87899895d6018097b19c39db569b52f7284ad0d59501401","sha256:586fd317ba0af12e0bf932a0d8756c92c49094d05389262ed90e817edf482e70"],"state_sha256":"2a29ba25724bf5a0f4cdcb6d4d2bf05cf30ae8e87f9f69fc6fd430b26083e5ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5tmEty3FJgZKuoSE6gn87wUlrIXdxVtUPXYbpSPzCwEI5EFR+lPtPKQXTVVoVd1kK7lJueJ7ULM4gnb3N1nDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:44:35.396324Z","bundle_sha256":"614faadef46bc59f702765728dea595a95d37a6b50ebf908edadb7dd5bbfb681"}}