{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KAKXCTOPR5BXI4DLUC3SO4WXD6","short_pith_number":"pith:KAKXCTOP","canonical_record":{"source":{"id":"2507.22612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T12:31:11Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"98fbe7aa3f5b20b0efc379fc42601385e5b46004b572dad128efbe0fbc4a1ae2","abstract_canon_sha256":"e362f33e390c3bc8688014e31cbf379f224b1c85b24293729f8963629abc2f00"},"schema_version":"1.0"},"canonical_sha256":"5015714dcf8f4374706ba0b72772d71f9a00c0f4f038b5e79e4d58ad75b5e263","source":{"kind":"arxiv","id":"2507.22612","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22612","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22612v2","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22612","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"KAKXCTOPR5BX","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"KAKXCTOPR5BXI4DL","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"KAKXCTOP","created_at":"2026-07-05T12:01:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KAKXCTOPR5BXI4DLUC3SO4WXD6","target":"record","payload":{"canonical_record":{"source":{"id":"2507.22612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T12:31:11Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"98fbe7aa3f5b20b0efc379fc42601385e5b46004b572dad128efbe0fbc4a1ae2","abstract_canon_sha256":"e362f33e390c3bc8688014e31cbf379f224b1c85b24293729f8963629abc2f00"},"schema_version":"1.0"},"canonical_sha256":"5015714dcf8f4374706ba0b72772d71f9a00c0f4f038b5e79e4d58ad75b5e263","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:25.254066Z","signature_b64":"td8jaZD+9suPK+blS0t7eR3wGloVnGmdaAmAJra9HU7UoaQn4guv7EtOdhZuUBXMJugy2LRI7HhnY1fZCqi0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5015714dcf8f4374706ba0b72772d71f9a00c0f4f038b5e79e4d58ad75b5e263","last_reissued_at":"2026-07-05T12:01:25.253488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:25.253488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.22612","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":"2026-07-05T12:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0bwDjNta86g1HyDnr6hk0N25k5S3iZT+cw6LsbqOzL/gDfUmPKsBBjCmGhPz/bfDEAaPG+Oxliw9xywK2noAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:43:02.033369Z"},"content_sha256":"56fde27dd09352ea366c2f4857e665aa1f39aa4912c7eccaa7ace0cb24d50575","schema_version":"1.0","event_id":"sha256:56fde27dd09352ea366c2f4857e665aa1f39aa4912c7eccaa7ace0cb24d50575"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KAKXCTOPR5BXI4DLUC3SO4WXD6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Duration Model for Text Speech Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Junjie Cao","submitted_at":"2025-07-30T12:31:11Z","abstract_excerpt":"Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line, while non-autoregressive end to end TTS models rely on durations extracted from external sources. In this paper, we propose a novel duration prediction framework that can give promising phoneme-level duration distribution with given text. In our experiments, the proposed duration model has more precise prediction and adaptation ability to conditions, compared to previous baseline models. Specifically, it makes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22612","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/2507.22612/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":"2026-07-05T12:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bYFrR96qL4b246S+m9h/Jt18I7VlMGldZqn5ghfKNzWTQdOi8yWOGed99eEy7Vatu1TpT0tTIUFWJiGTwS76CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:43:02.034275Z"},"content_sha256":"3231f9626cf18562e008e5c92da5ae5bf031545eb5b1ca964db7104e97101e60","schema_version":"1.0","event_id":"sha256:3231f9626cf18562e008e5c92da5ae5bf031545eb5b1ca964db7104e97101e60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KAKXCTOPR5BXI4DLUC3SO4WXD6/bundle.json","state_url":"https://pith.science/pith/KAKXCTOPR5BXI4DLUC3SO4WXD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KAKXCTOPR5BXI4DLUC3SO4WXD6/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":"2026-08-10T14:43:02Z","links":{"resolver":"https://pith.science/pith/KAKXCTOPR5BXI4DLUC3SO4WXD6","bundle":"https://pith.science/pith/KAKXCTOPR5BXI4DLUC3SO4WXD6/bundle.json","state":"https://pith.science/pith/KAKXCTOPR5BXI4DLUC3SO4WXD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KAKXCTOPR5BXI4DLUC3SO4WXD6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KAKXCTOPR5BXI4DLUC3SO4WXD6","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":"e362f33e390c3bc8688014e31cbf379f224b1c85b24293729f8963629abc2f00","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T12:31:11Z","title_canon_sha256":"98fbe7aa3f5b20b0efc379fc42601385e5b46004b572dad128efbe0fbc4a1ae2"},"schema_version":"1.0","source":{"id":"2507.22612","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22612","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22612v2","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22612","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"KAKXCTOPR5BX","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"KAKXCTOPR5BXI4DL","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"KAKXCTOP","created_at":"2026-07-05T12:01:25Z"}],"graph_snapshots":[{"event_id":"sha256:3231f9626cf18562e008e5c92da5ae5bf031545eb5b1ca964db7104e97101e60","target":"graph","created_at":"2026-07-05T12:01:25Z","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/2507.22612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line, while non-autoregressive end to end TTS models rely on durations extracted from external sources. In this paper, we propose a novel duration prediction framework that can give promising phoneme-level duration distribution with given text. In our experiments, the proposed duration model has more precise prediction and adaptation ability to conditions, compared to previous baseline models. Specifically, it makes ","authors_text":"Junjie Cao","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T12:31:11Z","title":"Adaptive Duration Model for Text Speech Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22612","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":"sha256:56fde27dd09352ea366c2f4857e665aa1f39aa4912c7eccaa7ace0cb24d50575","target":"record","created_at":"2026-07-05T12:01:25Z","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":"e362f33e390c3bc8688014e31cbf379f224b1c85b24293729f8963629abc2f00","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T12:31:11Z","title_canon_sha256":"98fbe7aa3f5b20b0efc379fc42601385e5b46004b572dad128efbe0fbc4a1ae2"},"schema_version":"1.0","source":{"id":"2507.22612","kind":"arxiv","version":2}},"canonical_sha256":"5015714dcf8f4374706ba0b72772d71f9a00c0f4f038b5e79e4d58ad75b5e263","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5015714dcf8f4374706ba0b72772d71f9a00c0f4f038b5e79e4d58ad75b5e263","first_computed_at":"2026-07-05T12:01:25.253488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:25.253488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"td8jaZD+9suPK+blS0t7eR3wGloVnGmdaAmAJra9HU7UoaQn4guv7EtOdhZuUBXMJugy2LRI7HhnY1fZCqi0AA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:25.254066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22612","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56fde27dd09352ea366c2f4857e665aa1f39aa4912c7eccaa7ace0cb24d50575","sha256:3231f9626cf18562e008e5c92da5ae5bf031545eb5b1ca964db7104e97101e60"],"state_sha256":"67a10614e8086dd1f5773fed3875101958735615187a162c98d12c14997684ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FvjaaO5HQglR4vGdTa0gCkxyzhmu9zArqWTlT/ANXNdpn9vsOtSDclpZac0CFGwQ/SoCyJ6vTnb/TI+nXdmdAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:43:02.042048Z","bundle_sha256":"3198f11f783d8d60f16e626c90653451d1ab230645dc44f607a34285e2d15f88"}}