{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3I77E4PV2AI3TLR2A4HY23TOAP","short_pith_number":"pith:3I77E4PV","schema_version":"1.0","canonical_sha256":"da3ff271f5d011b9ae3a070f8d6e6e03c415e8ea0fd731c6e444e5559f9ebae4","source":{"kind":"arxiv","id":"1808.03113","version":1},"attestation_state":"computed","paper":{"title":"Rhythm-Flexible Voice Conversion without Parallel Data Using Cycle-GAN over Phoneme Posteriorgram Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Cheng-chieh Yeh, Hung-yi Lee, Ju-chieh Chou, Lin-shan Lee, Po-chun Hsu","submitted_at":"2018-08-09T12:32:23Z","abstract_excerpt":"Speaking rate refers to the average number of phonemes within some unit time, while the rhythmic patterns refer to duration distributions for realizations of different phonemes within different phonetic structures. Both are key components of prosody in speech, which is different for different speakers. Models like cycle-consistent adversarial network (Cycle-GAN) and variational auto-encoder (VAE) have been successfully applied to voice conversion tasks without parallel data. However, due to the neural network architectures and feature vectors chosen for these approaches, the length of the pred"},"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":"1808.03113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-08-09T12:32:23Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4d49e56d4d33dab7c353f220b5b1d23a3efcd011ec9e3c80eb2125f413108c3d","abstract_canon_sha256":"3f40eeec2e7bf56f9d67eda9c580036de3a96c3946b6e5270e1bf87a01196131"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:30.167009Z","signature_b64":"wgBCv8Wt7U5tCZgOndOVzJojRc9qXhcyOj0UNfYRaqwGGnuxve5BU7Cc01m3vLQ/akcxuluCD8vU/CwK75yTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da3ff271f5d011b9ae3a070f8d6e6e03c415e8ea0fd731c6e444e5559f9ebae4","last_reissued_at":"2026-05-18T00:08:30.166521Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:30.166521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rhythm-Flexible Voice Conversion without Parallel Data Using Cycle-GAN over Phoneme Posteriorgram Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Cheng-chieh Yeh, Hung-yi Lee, Ju-chieh Chou, Lin-shan Lee, Po-chun Hsu","submitted_at":"2018-08-09T12:32:23Z","abstract_excerpt":"Speaking rate refers to the average number of phonemes within some unit time, while the rhythmic patterns refer to duration distributions for realizations of different phonemes within different phonetic structures. Both are key components of prosody in speech, which is different for different speakers. Models like cycle-consistent adversarial network (Cycle-GAN) and variational auto-encoder (VAE) have been successfully applied to voice conversion tasks without parallel data. However, due to the neural network architectures and feature vectors chosen for these approaches, the length of the pred"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03113","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":""},"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":"1808.03113","created_at":"2026-05-18T00:08:30.166585+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.03113v1","created_at":"2026-05-18T00:08:30.166585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03113","created_at":"2026-05-18T00:08:30.166585+00:00"},{"alias_kind":"pith_short_12","alias_value":"3I77E4PV2AI3","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3I77E4PV2AI3TLR2","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3I77E4PV","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3I77E4PV2AI3TLR2A4HY23TOAP","json":"https://pith.science/pith/3I77E4PV2AI3TLR2A4HY23TOAP.json","graph_json":"https://pith.science/api/pith-number/3I77E4PV2AI3TLR2A4HY23TOAP/graph.json","events_json":"https://pith.science/api/pith-number/3I77E4PV2AI3TLR2A4HY23TOAP/events.json","paper":"https://pith.science/paper/3I77E4PV"},"agent_actions":{"view_html":"https://pith.science/pith/3I77E4PV2AI3TLR2A4HY23TOAP","download_json":"https://pith.science/pith/3I77E4PV2AI3TLR2A4HY23TOAP.json","view_paper":"https://pith.science/paper/3I77E4PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.03113&json=true","fetch_graph":"https://pith.science/api/pith-number/3I77E4PV2AI3TLR2A4HY23TOAP/graph.json","fetch_events":"https://pith.science/api/pith-number/3I77E4PV2AI3TLR2A4HY23TOAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3I77E4PV2AI3TLR2A4HY23TOAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3I77E4PV2AI3TLR2A4HY23TOAP/action/storage_attestation","attest_author":"https://pith.science/pith/3I77E4PV2AI3TLR2A4HY23TOAP/action/author_attestation","sign_citation":"https://pith.science/pith/3I77E4PV2AI3TLR2A4HY23TOAP/action/citation_signature","submit_replication":"https://pith.science/pith/3I77E4PV2AI3TLR2A4HY23TOAP/action/replication_record"}},"created_at":"2026-05-18T00:08:30.166585+00:00","updated_at":"2026-05-18T00:08:30.166585+00:00"}