{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3CYQRHF2HTKKI2RESQ4CUHXPPB","short_pith_number":"pith:3CYQRHF2","canonical_record":{"source":{"id":"2508.04195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-06T08:25:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4002aa265a5dd1c603168f48a13b7de5f7073a6b5bc7a93bbca639930af98386","abstract_canon_sha256":"be8e685b840de450e2dc01ed5a82483c68e46720882db4679b04e89d561512c4"},"schema_version":"1.0"},"canonical_sha256":"d8b1089cba3cd4a46a2494382a1eef7862e2dce507f47abaa9575f59a46b10a3","source":{"kind":"arxiv","id":"2508.04195","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04195","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04195v1","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04195","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"pith_short_12","alias_value":"3CYQRHF2HTKK","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"pith_short_16","alias_value":"3CYQRHF2HTKKI2RE","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"pith_short_8","alias_value":"3CYQRHF2","created_at":"2026-07-05T11:49:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3CYQRHF2HTKKI2RESQ4CUHXPPB","target":"record","payload":{"canonical_record":{"source":{"id":"2508.04195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-06T08:25:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4002aa265a5dd1c603168f48a13b7de5f7073a6b5bc7a93bbca639930af98386","abstract_canon_sha256":"be8e685b840de450e2dc01ed5a82483c68e46720882db4679b04e89d561512c4"},"schema_version":"1.0"},"canonical_sha256":"d8b1089cba3cd4a46a2494382a1eef7862e2dce507f47abaa9575f59a46b10a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:22.534140Z","signature_b64":"ptpWLeUBeKY4B5dbUIvROXkNvhgbJERaWIwPuwmxN40mZzFB/6G82FJwQI1zFo8nio4jPH5giqaMPdrV9bRZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8b1089cba3cd4a46a2494382a1eef7862e2dce507f47abaa9575f59a46b10a3","last_reissued_at":"2026-07-05T11:49:22.533678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:22.533678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.04195","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":"2026-07-05T11:49:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LTMLGVXExyogtwvMGfahGhsEEfNh/lcI/y/0LdFrHLms+Jd0AC7q7hxWfDh01BMQ7RKa2bQlo9eQNpju2d6fDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:29:31.935404Z"},"content_sha256":"dc83185df600d3830da135cc25b36d8dcd021622631e1bdbcd664334c9eabb7c","schema_version":"1.0","event_id":"sha256:dc83185df600d3830da135cc25b36d8dcd021622631e1bdbcd664334c9eabb7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3CYQRHF2HTKKI2RESQ4CUHXPPB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SD","authors_text":"Haoyue Zhan, Huan Liao, Pengyuan Xie, Qiang Zhang, Qinke Ni, Yiheng Lu, Yuancheng Wang, Zhizheng Wu","submitted_at":"2025-08-06T08:25:26Z","abstract_excerpt":"Paralinguistic vocalizations-including non-verbal sounds like laughter and breathing, as well as lexicalized interjections such as \"uhm\" and \"oh\"-are integral to natural spoken communication. Despite their importance in conveying affect, intent, and interactional cues, such cues remain largely overlooked in conventional automatic speech recognition (ASR) and text-to-speech (TTS) systems. We present NVSpeech, an integrated and scalable pipeline that bridges the recognition and synthesis of paralinguistic vocalizations, encompassing dataset construction, ASR modeling, and controllable TTS. (1) W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04195","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/2508.04195/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":"2026-07-05T11:49:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7pTfnuy5JroMrtzpcfzAcskGKHKHEVxMtQvkYygw1FTiQpU3sbgiYre8cGWD8kw9kh6dYCyS1mrEoPIYLCUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:29:31.935891Z"},"content_sha256":"c712b32aa674b0aec386225c8551b43c00307b9d15080ee3b10fe21f29696b82","schema_version":"1.0","event_id":"sha256:c712b32aa674b0aec386225c8551b43c00307b9d15080ee3b10fe21f29696b82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CYQRHF2HTKKI2RESQ4CUHXPPB/bundle.json","state_url":"https://pith.science/pith/3CYQRHF2HTKKI2RESQ4CUHXPPB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CYQRHF2HTKKI2RESQ4CUHXPPB/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":"2026-08-06T15:29:31Z","links":{"resolver":"https://pith.science/pith/3CYQRHF2HTKKI2RESQ4CUHXPPB","bundle":"https://pith.science/pith/3CYQRHF2HTKKI2RESQ4CUHXPPB/bundle.json","state":"https://pith.science/pith/3CYQRHF2HTKKI2RESQ4CUHXPPB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CYQRHF2HTKKI2RESQ4CUHXPPB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3CYQRHF2HTKKI2RESQ4CUHXPPB","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":"be8e685b840de450e2dc01ed5a82483c68e46720882db4679b04e89d561512c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-06T08:25:26Z","title_canon_sha256":"4002aa265a5dd1c603168f48a13b7de5f7073a6b5bc7a93bbca639930af98386"},"schema_version":"1.0","source":{"id":"2508.04195","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04195","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04195v1","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04195","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"pith_short_12","alias_value":"3CYQRHF2HTKK","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"pith_short_16","alias_value":"3CYQRHF2HTKKI2RE","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"pith_short_8","alias_value":"3CYQRHF2","created_at":"2026-07-05T11:49:22Z"}],"graph_snapshots":[{"event_id":"sha256:c712b32aa674b0aec386225c8551b43c00307b9d15080ee3b10fe21f29696b82","target":"graph","created_at":"2026-07-05T11:49:22Z","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/2508.04195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Paralinguistic vocalizations-including non-verbal sounds like laughter and breathing, as well as lexicalized interjections such as \"uhm\" and \"oh\"-are integral to natural spoken communication. Despite their importance in conveying affect, intent, and interactional cues, such cues remain largely overlooked in conventional automatic speech recognition (ASR) and text-to-speech (TTS) systems. We present NVSpeech, an integrated and scalable pipeline that bridges the recognition and synthesis of paralinguistic vocalizations, encompassing dataset construction, ASR modeling, and controllable TTS. (1) W","authors_text":"Haoyue Zhan, Huan Liao, Pengyuan Xie, Qiang Zhang, Qinke Ni, Yiheng Lu, Yuancheng Wang, Zhizheng Wu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-06T08:25:26Z","title":"NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04195","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:dc83185df600d3830da135cc25b36d8dcd021622631e1bdbcd664334c9eabb7c","target":"record","created_at":"2026-07-05T11:49:22Z","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":"be8e685b840de450e2dc01ed5a82483c68e46720882db4679b04e89d561512c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-06T08:25:26Z","title_canon_sha256":"4002aa265a5dd1c603168f48a13b7de5f7073a6b5bc7a93bbca639930af98386"},"schema_version":"1.0","source":{"id":"2508.04195","kind":"arxiv","version":1}},"canonical_sha256":"d8b1089cba3cd4a46a2494382a1eef7862e2dce507f47abaa9575f59a46b10a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8b1089cba3cd4a46a2494382a1eef7862e2dce507f47abaa9575f59a46b10a3","first_computed_at":"2026-07-05T11:49:22.533678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:22.533678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ptpWLeUBeKY4B5dbUIvROXkNvhgbJERaWIwPuwmxN40mZzFB/6G82FJwQI1zFo8nio4jPH5giqaMPdrV9bRZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:22.534140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04195","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc83185df600d3830da135cc25b36d8dcd021622631e1bdbcd664334c9eabb7c","sha256:c712b32aa674b0aec386225c8551b43c00307b9d15080ee3b10fe21f29696b82"],"state_sha256":"c204e39c48a5113debe6af06c916ddb0ae211e8eb3d7761dce04aceaa148297b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcd6NUtBdGYTvXofmbZCTQ1efkpYyG5lefmC+j4kiPnA1sGuok9fvLXiXAAieI2h4rKJvS7u4VzEdrvxoVW6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:29:31.939765Z","bundle_sha256":"0df81d478f54195efefc6edbd64d73c9b0bbe53b5b1c55487c3c53b60fc9de47"}}