{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RRN6EL5NIXXIWNZNISLLNQNTWC","short_pith_number":"pith:RRN6EL5N","canonical_record":{"source":{"id":"2406.05401","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-08T08:49:22Z","cross_cats_sorted":["cs.HC","cs.SD"],"title_canon_sha256":"dbf73f0a654d6003dd0beeed2b50d37907db60fa792f453a76812d3983599aa0","abstract_canon_sha256":"ebfbdb60708f1c4a2ad21c5eab96db883b301aec7fd056bf5d403d4b0379ca5c"},"schema_version":"1.0"},"canonical_sha256":"8c5be22fad45ee8b372d4496b6c1b3b0ad796f61105a688a7e125ede9a57dafb","source":{"kind":"arxiv","id":"2406.05401","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05401","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05401v1","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05401","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"RRN6EL5NIXXI","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"RRN6EL5NIXXIWNZN","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"RRN6EL5N","created_at":"2026-07-05T08:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RRN6EL5NIXXIWNZNISLLNQNTWC","target":"record","payload":{"canonical_record":{"source":{"id":"2406.05401","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-08T08:49:22Z","cross_cats_sorted":["cs.HC","cs.SD"],"title_canon_sha256":"dbf73f0a654d6003dd0beeed2b50d37907db60fa792f453a76812d3983599aa0","abstract_canon_sha256":"ebfbdb60708f1c4a2ad21c5eab96db883b301aec7fd056bf5d403d4b0379ca5c"},"schema_version":"1.0"},"canonical_sha256":"8c5be22fad45ee8b372d4496b6c1b3b0ad796f61105a688a7e125ede9a57dafb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:05.027784Z","signature_b64":"yoyUfkOiSoisQnys6y8Ig6MxFPzxv41G4FPQnXCV1NJKPD+gPq0TGRHYGaZkzMSn5t5UTaSWnBl6gkfas9dTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c5be22fad45ee8b372d4496b6c1b3b0ad796f61105a688a7e125ede9a57dafb","last_reissued_at":"2026-07-05T08:29:05.027272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:05.027272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.05401","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":"2026-07-05T08:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KRWi3stbh1vPRJ4EOZrFDoMjWLzSSQ7yQ/3LUD1arr5nQTYQQzt8t+Nk9wDUx4eNE07Af5zJMfVzBK2wS0Z1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:34:11.635267Z"},"content_sha256":"26694a65ed33bfe28a33e27ba221928c12e108fe27f63f88df74e8d2fa8a83fd","schema_version":"1.0","event_id":"sha256:26694a65ed33bfe28a33e27ba221928c12e108fe27f63f88df74e8d2fa8a83fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RRN6EL5NIXXIWNZNISLLNQNTWC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.SD"],"primary_cat":"eess.AS","authors_text":"\\'Eva Sz\\'ekely, Gustav Eje Henter, Harm Lameris, Jonas Beskow, Rajiv Punmiya, Shivam Mehta","submitted_at":"2024-06-08T08:49:22Z","abstract_excerpt":"Converting input symbols to output audio in TTS requires modelling the durations of speech sounds. Leading non-autoregressive (NAR) TTS models treat duration modelling as a regression problem. The same utterance is then spoken with identical timings every time, unlike when a human speaks. Probabilistic models of duration have been proposed, but there is mixed evidence of their benefits. However, prior studies generally only consider speech read aloud, and ignore spontaneous speech, despite the latter being both a more common and a more variable mode of speaking. We compare the effect of conven"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05401","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/2406.05401/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":"2026-07-05T08:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xcvbeVn9EvpNgMOhWB1J1x3ws5Gz2FJOQfV2u6v6vIoNOmBEHhU1mt8OFzL4tqLZ4GumOzaoSQVkGinqg75uAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:34:11.635784Z"},"content_sha256":"dadadc0b5d8bdb8bcb2a9e65e7198f1446088bfc2ca5eed2aa837d1f6edc22db","schema_version":"1.0","event_id":"sha256:dadadc0b5d8bdb8bcb2a9e65e7198f1446088bfc2ca5eed2aa837d1f6edc22db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRN6EL5NIXXIWNZNISLLNQNTWC/bundle.json","state_url":"https://pith.science/pith/RRN6EL5NIXXIWNZNISLLNQNTWC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRN6EL5NIXXIWNZNISLLNQNTWC/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":"2026-08-10T19:34:11Z","links":{"resolver":"https://pith.science/pith/RRN6EL5NIXXIWNZNISLLNQNTWC","bundle":"https://pith.science/pith/RRN6EL5NIXXIWNZNISLLNQNTWC/bundle.json","state":"https://pith.science/pith/RRN6EL5NIXXIWNZNISLLNQNTWC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRN6EL5NIXXIWNZNISLLNQNTWC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RRN6EL5NIXXIWNZNISLLNQNTWC","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":"ebfbdb60708f1c4a2ad21c5eab96db883b301aec7fd056bf5d403d4b0379ca5c","cross_cats_sorted":["cs.HC","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-08T08:49:22Z","title_canon_sha256":"dbf73f0a654d6003dd0beeed2b50d37907db60fa792f453a76812d3983599aa0"},"schema_version":"1.0","source":{"id":"2406.05401","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05401","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05401v1","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05401","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"RRN6EL5NIXXI","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"RRN6EL5NIXXIWNZN","created_at":"2026-07-05T08:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"RRN6EL5N","created_at":"2026-07-05T08:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:dadadc0b5d8bdb8bcb2a9e65e7198f1446088bfc2ca5eed2aa837d1f6edc22db","target":"graph","created_at":"2026-07-05T08:29:05Z","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/2406.05401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Converting input symbols to output audio in TTS requires modelling the durations of speech sounds. Leading non-autoregressive (NAR) TTS models treat duration modelling as a regression problem. The same utterance is then spoken with identical timings every time, unlike when a human speaks. Probabilistic models of duration have been proposed, but there is mixed evidence of their benefits. However, prior studies generally only consider speech read aloud, and ignore spontaneous speech, despite the latter being both a more common and a more variable mode of speaking. We compare the effect of conven","authors_text":"\\'Eva Sz\\'ekely, Gustav Eje Henter, Harm Lameris, Jonas Beskow, Rajiv Punmiya, Shivam Mehta","cross_cats":["cs.HC","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-08T08:49:22Z","title":"Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05401","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":"sha256:26694a65ed33bfe28a33e27ba221928c12e108fe27f63f88df74e8d2fa8a83fd","target":"record","created_at":"2026-07-05T08:29:05Z","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":"ebfbdb60708f1c4a2ad21c5eab96db883b301aec7fd056bf5d403d4b0379ca5c","cross_cats_sorted":["cs.HC","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-08T08:49:22Z","title_canon_sha256":"dbf73f0a654d6003dd0beeed2b50d37907db60fa792f453a76812d3983599aa0"},"schema_version":"1.0","source":{"id":"2406.05401","kind":"arxiv","version":1}},"canonical_sha256":"8c5be22fad45ee8b372d4496b6c1b3b0ad796f61105a688a7e125ede9a57dafb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c5be22fad45ee8b372d4496b6c1b3b0ad796f61105a688a7e125ede9a57dafb","first_computed_at":"2026-07-05T08:29:05.027272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:05.027272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yoyUfkOiSoisQnys6y8Ig6MxFPzxv41G4FPQnXCV1NJKPD+gPq0TGRHYGaZkzMSn5t5UTaSWnBl6gkfas9dTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:05.027784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05401","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26694a65ed33bfe28a33e27ba221928c12e108fe27f63f88df74e8d2fa8a83fd","sha256:dadadc0b5d8bdb8bcb2a9e65e7198f1446088bfc2ca5eed2aa837d1f6edc22db"],"state_sha256":"e0ca661f6f51682866c94cabdb655fcc46b8d2702c90e33b1b391683311a3297"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vJDxqGM2nh5Yqg/86R6XHnhQ/oPQt1cWMO0qLqns7iffoTnONTkvF4N0mIgxzDma54DU3YgSkEm6T+4vRDYUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:34:11.643242Z","bundle_sha256":"08138e19c84d0196f7adc771809c31cfd41918da10ea5dd0f55758ba68158f3f"}}