{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2J6MDGB7LOV3GUMJFNKPZJN7B4","short_pith_number":"pith:2J6MDGB7","schema_version":"1.0","canonical_sha256":"d27cc1983f5babb351892b54fca5bf0f13e2a5045d339dc4b6cf5e4d93bab490","source":{"kind":"arxiv","id":"2507.13155","version":1},"attestation_state":"computed","paper":{"title":"NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Daria Diatlova, Egor Spirin, Maksim Borisov","submitted_at":"2025-07-17T14:17:40Z","abstract_excerpt":"Current expressive speech synthesis models are constrained by the limited availability of open-source datasets containing diverse nonverbal vocalizations (NVs). In this work, we introduce NonverbalTTS (NVTTS), a 17-hour open-access dataset annotated with 10 types of NVs (e.g., laughter, coughs) and 8 emotional categories. The dataset is derived from popular sources, VoxCeleb and Expresso, using automated detection followed by human validation. We propose a comprehensive pipeline that integrates automatic speech recognition (ASR), NV tagging, emotion classification, and a fusion algorithm to me"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.13155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T14:17:40Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d6325c65aae1103e126990af4555c6970c12e3948f7e5c618e99459ab5d34eb6","abstract_canon_sha256":"a16e87af781fed65d72356a1175fc25ba78b08883b84940dff3ca5e9353065c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:55.605012Z","signature_b64":"NF7CwraGehdR/IAJRH4f9MFXBp4NaYM/DPC/tr4IdQKub36CdeLMgViI8pAkat6PB0lxTQRtWGmgVHvV2sekCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d27cc1983f5babb351892b54fca5bf0f13e2a5045d339dc4b6cf5e4d93bab490","last_reissued_at":"2026-07-05T11:38:55.604527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:55.604527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Daria Diatlova, Egor Spirin, Maksim Borisov","submitted_at":"2025-07-17T14:17:40Z","abstract_excerpt":"Current expressive speech synthesis models are constrained by the limited availability of open-source datasets containing diverse nonverbal vocalizations (NVs). In this work, we introduce NonverbalTTS (NVTTS), a 17-hour open-access dataset annotated with 10 types of NVs (e.g., laughter, coughs) and 8 emotional categories. The dataset is derived from popular sources, VoxCeleb and Expresso, using automated detection followed by human validation. We propose a comprehensive pipeline that integrates automatic speech recognition (ASR), NV tagging, emotion classification, and a fusion algorithm to me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13155","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/2507.13155/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.13155","created_at":"2026-07-05T11:38:55.604588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13155v1","created_at":"2026-07-05T11:38:55.604588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13155","created_at":"2026-07-05T11:38:55.604588+00:00"},{"alias_kind":"pith_short_12","alias_value":"2J6MDGB7LOV3","created_at":"2026-07-05T11:38:55.604588+00:00"},{"alias_kind":"pith_short_16","alias_value":"2J6MDGB7LOV3GUMJ","created_at":"2026-07-05T11:38:55.604588+00:00"},{"alias_kind":"pith_short_8","alias_value":"2J6MDGB7","created_at":"2026-07-05T11:38:55.604588+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21215","citing_title":"Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01804","citing_title":"SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25504","citing_title":"Toward Natural Emotional Text-To-Speech System with Fine-Grained Non-Verbal Expression Control","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12036","citing_title":"Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16211","citing_title":"NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17435","citing_title":"MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4","json":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4.json","graph_json":"https://pith.science/api/pith-number/2J6MDGB7LOV3GUMJFNKPZJN7B4/graph.json","events_json":"https://pith.science/api/pith-number/2J6MDGB7LOV3GUMJFNKPZJN7B4/events.json","paper":"https://pith.science/paper/2J6MDGB7"},"agent_actions":{"view_html":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4","download_json":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4.json","view_paper":"https://pith.science/paper/2J6MDGB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13155&json=true","fetch_graph":"https://pith.science/api/pith-number/2J6MDGB7LOV3GUMJFNKPZJN7B4/graph.json","fetch_events":"https://pith.science/api/pith-number/2J6MDGB7LOV3GUMJFNKPZJN7B4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/action/storage_attestation","attest_author":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/action/author_attestation","sign_citation":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/action/citation_signature","submit_replication":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/action/replication_record"}},"created_at":"2026-07-05T11:38:55.604588+00:00","updated_at":"2026-07-05T11:38:55.604588+00:00"}