{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YKLVJ4YYMFOFWSKYMAH7X36SP2","short_pith_number":"pith:YKLVJ4YY","canonical_record":{"source":{"id":"2401.08095","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-16T03:39:35Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"dc64bdc3df1519c85664a7c8f9a1803d278cba3a71aaedf9f94335b5578bbd09","abstract_canon_sha256":"1b77f2fbc1c9096b7b014034bcd2622df81701b00cefacab79449b1f6ae23162"},"schema_version":"1.0"},"canonical_sha256":"c29754f318615c5b4958600ffbefd27eb0c705056e179f16dec3ad51a88d6e62","source":{"kind":"arxiv","id":"2401.08095","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08095","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08095v4","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08095","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"pith_short_12","alias_value":"YKLVJ4YYMFOF","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"pith_short_16","alias_value":"YKLVJ4YYMFOFWSKY","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"pith_short_8","alias_value":"YKLVJ4YY","created_at":"2026-07-05T10:02:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YKLVJ4YYMFOFWSKYMAH7X36SP2","target":"record","payload":{"canonical_record":{"source":{"id":"2401.08095","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-16T03:39:35Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"dc64bdc3df1519c85664a7c8f9a1803d278cba3a71aaedf9f94335b5578bbd09","abstract_canon_sha256":"1b77f2fbc1c9096b7b014034bcd2622df81701b00cefacab79449b1f6ae23162"},"schema_version":"1.0"},"canonical_sha256":"c29754f318615c5b4958600ffbefd27eb0c705056e179f16dec3ad51a88d6e62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:43.056580Z","signature_b64":"oBRngk9do+DeNJ6PYkS8I/G+oRoypWYJcoShrvcNKvkPPBL78i4P1nb1Ov8/RhgmozNULzxNqJoQEzhd+/g0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c29754f318615c5b4958600ffbefd27eb0c705056e179f16dec3ad51a88d6e62","last_reissued_at":"2026-07-05T10:02:43.056078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:43.056078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.08095","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZsQ9UdcdTmIUqnWyx/cUvYgCoOEfw5U1NNLSOq8ixykKvulYyzwRxnp5CNjQmWnnUTANz8GZ6u8++lH/f/TgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:12:39.334103Z"},"content_sha256":"2c457785b8b5a6eeef2d2c374942bb4657c2eaa9c87464cb33b3a9ccf9281bd9","schema_version":"1.0","event_id":"sha256:2c457785b8b5a6eeef2d2c374942bb4657c2eaa9c87464cb33b3a9ccf9281bd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YKLVJ4YYMFOFWSKYMAH7X36SP2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Deok-Hyeon Cho, Hyung-Seok Oh, Sang-Hoon Lee, Seong-Whan Lee","submitted_at":"2024-01-16T03:39:35Z","abstract_excerpt":"Emotional voice conversion (EVC) involves modifying various acoustic characteristics, such as pitch and spectral envelope, to match a desired emotional state while preserving the speaker's identity. Existing EVC methods often rely on text transcriptions or time-alignment information and struggle to handle varying speech durations effectively. In this paper, we propose DurFlex-EVC, a duration-flexible EVC framework that operates without the need for text or alignment information. We introduce a unit aligner that models contextual information by aligning speech with discrete units representing c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08095","kind":"arxiv","version":4},"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/2401.08095/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":"2026-07-05T10:02:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qm9QXV+5AzggbtO6YozwT29nZlG4eXUNGD/r1Wakh0t5bnPvmcNemrXcQYmbZX2iRNx+3cCCNePxk0rRNrr9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:12:39.335104Z"},"content_sha256":"169dd7b462b1e9d7a03d9877632d7c2d84dd522daaa77624bc4aff81605c53df","schema_version":"1.0","event_id":"sha256:169dd7b462b1e9d7a03d9877632d7c2d84dd522daaa77624bc4aff81605c53df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YKLVJ4YYMFOFWSKYMAH7X36SP2/bundle.json","state_url":"https://pith.science/pith/YKLVJ4YYMFOFWSKYMAH7X36SP2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YKLVJ4YYMFOFWSKYMAH7X36SP2/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":"2026-08-12T19:12:39Z","links":{"resolver":"https://pith.science/pith/YKLVJ4YYMFOFWSKYMAH7X36SP2","bundle":"https://pith.science/pith/YKLVJ4YYMFOFWSKYMAH7X36SP2/bundle.json","state":"https://pith.science/pith/YKLVJ4YYMFOFWSKYMAH7X36SP2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YKLVJ4YYMFOFWSKYMAH7X36SP2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YKLVJ4YYMFOFWSKYMAH7X36SP2","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":"1b77f2fbc1c9096b7b014034bcd2622df81701b00cefacab79449b1f6ae23162","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-16T03:39:35Z","title_canon_sha256":"dc64bdc3df1519c85664a7c8f9a1803d278cba3a71aaedf9f94335b5578bbd09"},"schema_version":"1.0","source":{"id":"2401.08095","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08095","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08095v4","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08095","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"pith_short_12","alias_value":"YKLVJ4YYMFOF","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"pith_short_16","alias_value":"YKLVJ4YYMFOFWSKY","created_at":"2026-07-05T10:02:43Z"},{"alias_kind":"pith_short_8","alias_value":"YKLVJ4YY","created_at":"2026-07-05T10:02:43Z"}],"graph_snapshots":[{"event_id":"sha256:169dd7b462b1e9d7a03d9877632d7c2d84dd522daaa77624bc4aff81605c53df","target":"graph","created_at":"2026-07-05T10:02:43Z","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/2401.08095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emotional voice conversion (EVC) involves modifying various acoustic characteristics, such as pitch and spectral envelope, to match a desired emotional state while preserving the speaker's identity. Existing EVC methods often rely on text transcriptions or time-alignment information and struggle to handle varying speech durations effectively. In this paper, we propose DurFlex-EVC, a duration-flexible EVC framework that operates without the need for text or alignment information. We introduce a unit aligner that models contextual information by aligning speech with discrete units representing c","authors_text":"Deok-Hyeon Cho, Hyung-Seok Oh, Sang-Hoon Lee, Seong-Whan Lee","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-16T03:39:35Z","title":"DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08095","kind":"arxiv","version":4},"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":"sha256:2c457785b8b5a6eeef2d2c374942bb4657c2eaa9c87464cb33b3a9ccf9281bd9","target":"record","created_at":"2026-07-05T10:02:43Z","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":"1b77f2fbc1c9096b7b014034bcd2622df81701b00cefacab79449b1f6ae23162","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-16T03:39:35Z","title_canon_sha256":"dc64bdc3df1519c85664a7c8f9a1803d278cba3a71aaedf9f94335b5578bbd09"},"schema_version":"1.0","source":{"id":"2401.08095","kind":"arxiv","version":4}},"canonical_sha256":"c29754f318615c5b4958600ffbefd27eb0c705056e179f16dec3ad51a88d6e62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c29754f318615c5b4958600ffbefd27eb0c705056e179f16dec3ad51a88d6e62","first_computed_at":"2026-07-05T10:02:43.056078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:43.056078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oBRngk9do+DeNJ6PYkS8I/G+oRoypWYJcoShrvcNKvkPPBL78i4P1nb1Ov8/RhgmozNULzxNqJoQEzhd+/g0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:43.056580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08095","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c457785b8b5a6eeef2d2c374942bb4657c2eaa9c87464cb33b3a9ccf9281bd9","sha256:169dd7b462b1e9d7a03d9877632d7c2d84dd522daaa77624bc4aff81605c53df"],"state_sha256":"17c5671a64e8390ef59322507a4a9442984238c84b64e0b7defa1a1711c89234"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wUzHb+z5ybSwUM8t7NDVJqYoiHaM5Lhe4IgbrGFE5OzA2NaPTlfYYboSNqmu7PmuL9eHh1KGAxl7moSF1+LoCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:12:39.342794Z","bundle_sha256":"a7007a1e956d9db38d177394f554259570a22bddd9ce86f49555ca24bafc88ca"}}