{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X7AVIAKD2ZUAN24TDIUQ5MSCA4","short_pith_number":"pith:X7AVIAKD","schema_version":"1.0","canonical_sha256":"bfc1540143d66806eb931a290eb24207328827b07cf6d8a4ae9b39c08e596ad2","source":{"kind":"arxiv","id":"2406.07254","version":1},"attestation_state":"computed","paper":{"title":"SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Kentaro Seki, Kentaro Tachibana, Ryuichi Yamamoto, Shinnosuke Takamichi, Takuto Igarashi, Yuki Saito","submitted_at":"2024-06-11T13:34:40Z","abstract_excerpt":"We present SRC4VC, a new corpus containing 11 hours of speech recorded on smartphones by 100 Japanese speakers. Although high-quality multi-speaker corpora can advance voice conversion (VC) technologies, they are not always suitable for testing VC when low-quality speech recording is given as the input. To this end, we first asked 100 crowdworkers to record their voice samples using smartphones. Then, we annotated the recorded samples with speaker-wise recording-quality scores and utterance-wise perceived emotion labels. We also benchmark SRC4VC on any-to-any VC, in which we trained a multi-sp"},"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":"2406.07254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T13:34:40Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fb3f2e4108ae71dcdc4f9c4e3723f1648c39b4292f5683a6328939bc992a66c1","abstract_canon_sha256":"da90080e3c140610a8feae7d5935024685df41d4ccf3624d5138212d88653857"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:20.638801Z","signature_b64":"bSRQEQdvHP27HHWrSEX17TlpOyC9ijXUDwDvFNENLdezoz0pqf7qpqkOOy1yTMFx0UjV2dRPx/apVVVdj14/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfc1540143d66806eb931a290eb24207328827b07cf6d8a4ae9b39c08e596ad2","last_reissued_at":"2026-07-05T08:30:20.638281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:20.638281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Kentaro Seki, Kentaro Tachibana, Ryuichi Yamamoto, Shinnosuke Takamichi, Takuto Igarashi, Yuki Saito","submitted_at":"2024-06-11T13:34:40Z","abstract_excerpt":"We present SRC4VC, a new corpus containing 11 hours of speech recorded on smartphones by 100 Japanese speakers. Although high-quality multi-speaker corpora can advance voice conversion (VC) technologies, they are not always suitable for testing VC when low-quality speech recording is given as the input. To this end, we first asked 100 crowdworkers to record their voice samples using smartphones. Then, we annotated the recorded samples with speaker-wise recording-quality scores and utterance-wise perceived emotion labels. We also benchmark SRC4VC on any-to-any VC, in which we trained a multi-sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07254","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/2406.07254/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":"2406.07254","created_at":"2026-07-05T08:30:20.638352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07254v1","created_at":"2026-07-05T08:30:20.638352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07254","created_at":"2026-07-05T08:30:20.638352+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7AVIAKD2ZUA","created_at":"2026-07-05T08:30:20.638352+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7AVIAKD2ZUAN24T","created_at":"2026-07-05T08:30:20.638352+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7AVIAKD","created_at":"2026-07-05T08:30:20.638352+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00251","citing_title":"Alethia: A Foundational Encoder for Voice Deepfakes","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X7AVIAKD2ZUAN24TDIUQ5MSCA4","json":"https://pith.science/pith/X7AVIAKD2ZUAN24TDIUQ5MSCA4.json","graph_json":"https://pith.science/api/pith-number/X7AVIAKD2ZUAN24TDIUQ5MSCA4/graph.json","events_json":"https://pith.science/api/pith-number/X7AVIAKD2ZUAN24TDIUQ5MSCA4/events.json","paper":"https://pith.science/paper/X7AVIAKD"},"agent_actions":{"view_html":"https://pith.science/pith/X7AVIAKD2ZUAN24TDIUQ5MSCA4","download_json":"https://pith.science/pith/X7AVIAKD2ZUAN24TDIUQ5MSCA4.json","view_paper":"https://pith.science/paper/X7AVIAKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07254&json=true","fetch_graph":"https://pith.science/api/pith-number/X7AVIAKD2ZUAN24TDIUQ5MSCA4/graph.json","fetch_events":"https://pith.science/api/pith-number/X7AVIAKD2ZUAN24TDIUQ5MSCA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7AVIAKD2ZUAN24TDIUQ5MSCA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7AVIAKD2ZUAN24TDIUQ5MSCA4/action/storage_attestation","attest_author":"https://pith.science/pith/X7AVIAKD2ZUAN24TDIUQ5MSCA4/action/author_attestation","sign_citation":"https://pith.science/pith/X7AVIAKD2ZUAN24TDIUQ5MSCA4/action/citation_signature","submit_replication":"https://pith.science/pith/X7AVIAKD2ZUAN24TDIUQ5MSCA4/action/replication_record"}},"created_at":"2026-07-05T08:30:20.638352+00:00","updated_at":"2026-07-05T08:30:20.638352+00:00"}