{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2Q6L6V7LVTK236KRNERDPF3YHE","short_pith_number":"pith:2Q6L6V7L","schema_version":"1.0","canonical_sha256":"d43cbf57ebacd5adf951692237977839163066db9297a9f543d5fbe150846a51","source":{"kind":"arxiv","id":"2411.09943","version":1},"attestation_state":"computed","paper":{"title":"Zero-shot Voice Conversion with Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Songting Liu","submitted_at":"2024-11-15T04:43:44Z","abstract_excerpt":"Zero-shot voice conversion aims to transform a source speech utterance to match the timbre of a reference speech from an unseen speaker. Traditional approaches struggle with timbre leakage, insufficient timbre representation, and mismatches between training and inference tasks. We propose Seed-VC, a novel framework that addresses these issues by introducing an external timbre shifter during training to perturb the source speech timbre, mitigating leakage and aligning training with inference. Additionally, we employ a diffusion transformer that leverages the entire reference speech context, cap"},"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":"2411.09943","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-15T04:43:44Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"e3087406d7cbbfe5a1d59480973fd5034710931ba64e46973725ed7b2fb0155c","abstract_canon_sha256":"65bd61972a0f8c37c8600326413d56e23ee0ea96b2c17e10f067143e9a00317c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:56.074948Z","signature_b64":"BPlbIsZUbpsunEDMIaGFHVS1dkLbiC2QzKIr01fpMEsMk87Giv4cEz04grgDaC3kGyNz+OXH/FJkO5NujBCcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d43cbf57ebacd5adf951692237977839163066db9297a9f543d5fbe150846a51","last_reissued_at":"2026-07-05T09:35:56.074411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:56.074411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-shot Voice Conversion with Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Songting Liu","submitted_at":"2024-11-15T04:43:44Z","abstract_excerpt":"Zero-shot voice conversion aims to transform a source speech utterance to match the timbre of a reference speech from an unseen speaker. Traditional approaches struggle with timbre leakage, insufficient timbre representation, and mismatches between training and inference tasks. We propose Seed-VC, a novel framework that addresses these issues by introducing an external timbre shifter during training to perturb the source speech timbre, mitigating leakage and aligning training with inference. Additionally, we employ a diffusion transformer that leverages the entire reference speech context, cap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09943","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/2411.09943/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":"2411.09943","created_at":"2026-07-05T09:35:56.074473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09943v1","created_at":"2026-07-05T09:35:56.074473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09943","created_at":"2026-07-05T09:35:56.074473+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Q6L6V7LVTK2","created_at":"2026-07-05T09:35:56.074473+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Q6L6V7LVTK236KR","created_at":"2026-07-05T09:35:56.074473+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Q6L6V7L","created_at":"2026-07-05T09:35:56.074473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21893","citing_title":"AugCodec: A Low-Bitrate Disentangled Neural Speech Codec via Data Augmentation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21888","citing_title":"ProsoCodec: Prosody-Oriented Speech Codec for Voice Conversion","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21215","citing_title":"Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20218","citing_title":"Zero-VC: Zero-Lookahead Streaming Voice Conversion via Speaker Anonymization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17126","citing_title":"Vibrato Expression Control for Singing Voice Conversion with Improving Independent Control","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09050","citing_title":"MeanVC 2: Robust Low-Latency Streaming Zero-Shot Voice Conversion","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01563","citing_title":"Beyond Words: Towards Effective Modeling of Non-Verbal Vocalizations in ASR","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08843","citing_title":"From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Data","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00363","citing_title":"Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01804","citing_title":"SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08843","citing_title":"From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Data","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20657","citing_title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13067","citing_title":"From Seeing it to Experiencing it: Interactive Evaluation of Intersectional Voice Bias in Human-AI Speech Interaction","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12310","citing_title":"Poly-SVC: Polyphony-Aware Singing Voice Conversion with Harmonic Modeling","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23742","citing_title":"RTCFake: Speech Deepfake Detection in Real-Time Communication","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19193","citing_title":"How Far Are Video Models from True Multimodal Reasoning?","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08184","citing_title":"AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12456","citing_title":"X-VC: Zero-shot Streaming Voice Conversion in Codec Space","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2Q6L6V7LVTK236KRNERDPF3YHE","json":"https://pith.science/pith/2Q6L6V7LVTK236KRNERDPF3YHE.json","graph_json":"https://pith.science/api/pith-number/2Q6L6V7LVTK236KRNERDPF3YHE/graph.json","events_json":"https://pith.science/api/pith-number/2Q6L6V7LVTK236KRNERDPF3YHE/events.json","paper":"https://pith.science/paper/2Q6L6V7L"},"agent_actions":{"view_html":"https://pith.science/pith/2Q6L6V7LVTK236KRNERDPF3YHE","download_json":"https://pith.science/pith/2Q6L6V7LVTK236KRNERDPF3YHE.json","view_paper":"https://pith.science/paper/2Q6L6V7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09943&json=true","fetch_graph":"https://pith.science/api/pith-number/2Q6L6V7LVTK236KRNERDPF3YHE/graph.json","fetch_events":"https://pith.science/api/pith-number/2Q6L6V7LVTK236KRNERDPF3YHE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Q6L6V7LVTK236KRNERDPF3YHE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Q6L6V7LVTK236KRNERDPF3YHE/action/storage_attestation","attest_author":"https://pith.science/pith/2Q6L6V7LVTK236KRNERDPF3YHE/action/author_attestation","sign_citation":"https://pith.science/pith/2Q6L6V7LVTK236KRNERDPF3YHE/action/citation_signature","submit_replication":"https://pith.science/pith/2Q6L6V7LVTK236KRNERDPF3YHE/action/replication_record"}},"created_at":"2026-07-05T09:35:56.074473+00:00","updated_at":"2026-07-05T09:35:56.074473+00:00"}