{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I3I6ABABPATEHWJDG5UASBYHIX","short_pith_number":"pith:I3I6ABAB","schema_version":"1.0","canonical_sha256":"46d1e00401782643d923376809070745e8520927ec200af84c9c6c200fec6d94","source":{"kind":"arxiv","id":"2104.01497","version":3},"attestation_state":"computed","paper":{"title":"Hi-Fi Multi-Speaker English TTS Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Evelina Bakhturina, Vitaly Lavrukhin, Yang Zhang","submitted_at":"2021-04-03T23:19:50Z","abstract_excerpt":"This paper introduces a new multi-speaker English dataset for training text-to-speech models. The dataset is based on LibriVox audiobooks and Project Gutenberg texts, both in the public domain. The new dataset contains about 292 hours of speech from 10 speakers with at least 17 hours per speaker sampled at 44.1 kHz. To select speech samples with high quality, we considered audio recordings with a signal bandwidth of at least 13 kHz and a signal-to-noise ratio (SNR) of at least 32 dB. The dataset is publicly released at http://www.openslr.org/109/ ."},"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":"2104.01497","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-03T23:19:50Z","cross_cats_sorted":[],"title_canon_sha256":"4eaeb0c6b275c43c94d17aa453439cc48df7acff982b0249ff205d998dce2cb9","abstract_canon_sha256":"a52c3be57adfa32d2745afccb4c222ca1cce935bd6ea1bf3f29a52ed0ed556a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:28.974907Z","signature_b64":"qEXnge+nQH0XuM+tKdKUhG8s/S+2lhyQZTuK5Fi2q0jubodFcQ/T8XuBnRNiesHposT2gzCfrZM1gyFlaQr6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d1e00401782643d923376809070745e8520927ec200af84c9c6c200fec6d94","last_reissued_at":"2026-07-05T02:49:28.974519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:28.974519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi-Fi Multi-Speaker English TTS Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Evelina Bakhturina, Vitaly Lavrukhin, Yang Zhang","submitted_at":"2021-04-03T23:19:50Z","abstract_excerpt":"This paper introduces a new multi-speaker English dataset for training text-to-speech models. The dataset is based on LibriVox audiobooks and Project Gutenberg texts, both in the public domain. The new dataset contains about 292 hours of speech from 10 speakers with at least 17 hours per speaker sampled at 44.1 kHz. To select speech samples with high quality, we considered audio recordings with a signal bandwidth of at least 13 kHz and a signal-to-noise ratio (SNR) of at least 32 dB. The dataset is publicly released at http://www.openslr.org/109/ ."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01497","kind":"arxiv","version":3},"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/2104.01497/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":"2104.01497","created_at":"2026-07-05T02:49:28.974568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01497v3","created_at":"2026-07-05T02:49:28.974568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01497","created_at":"2026-07-05T02:49:28.974568+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3I6ABABPATE","created_at":"2026-07-05T02:49:28.974568+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3I6ABABPATEHWJD","created_at":"2026-07-05T02:49:28.974568+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3I6ABAB","created_at":"2026-07-05T02:49:28.974568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22220","citing_title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":198,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I3I6ABABPATEHWJDG5UASBYHIX","json":"https://pith.science/pith/I3I6ABABPATEHWJDG5UASBYHIX.json","graph_json":"https://pith.science/api/pith-number/I3I6ABABPATEHWJDG5UASBYHIX/graph.json","events_json":"https://pith.science/api/pith-number/I3I6ABABPATEHWJDG5UASBYHIX/events.json","paper":"https://pith.science/paper/I3I6ABAB"},"agent_actions":{"view_html":"https://pith.science/pith/I3I6ABABPATEHWJDG5UASBYHIX","download_json":"https://pith.science/pith/I3I6ABABPATEHWJDG5UASBYHIX.json","view_paper":"https://pith.science/paper/I3I6ABAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01497&json=true","fetch_graph":"https://pith.science/api/pith-number/I3I6ABABPATEHWJDG5UASBYHIX/graph.json","fetch_events":"https://pith.science/api/pith-number/I3I6ABABPATEHWJDG5UASBYHIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3I6ABABPATEHWJDG5UASBYHIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3I6ABABPATEHWJDG5UASBYHIX/action/storage_attestation","attest_author":"https://pith.science/pith/I3I6ABABPATEHWJDG5UASBYHIX/action/author_attestation","sign_citation":"https://pith.science/pith/I3I6ABABPATEHWJDG5UASBYHIX/action/citation_signature","submit_replication":"https://pith.science/pith/I3I6ABABPATEHWJDG5UASBYHIX/action/replication_record"}},"created_at":"2026-07-05T02:49:28.974568+00:00","updated_at":"2026-07-05T02:49:28.974568+00:00"}