{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WU4J2Q624UFR2GLBFQSSJZUVRZ","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":"aaaffc114568f88e973f749ff8c98351af5d8dccd1d68fa238733d01255ebc67","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T10:59:29Z","title_canon_sha256":"74945a9cec14847d7ea91227d76528403843ead517aeb493680e4ecfedabd1a0"},"schema_version":"1.0","source":{"id":"2309.07598","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07598","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07598v2","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07598","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"WU4J2Q624UFR","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"WU4J2Q624UFR2GLB","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"WU4J2Q62","created_at":"2026-07-05T06:50:59Z"}],"graph_snapshots":[{"event_id":"sha256:0efe949978226e8b9fdccfd2ee0c45267094ad3f0e9368cf9c437b382a2d55d3","target":"graph","created_at":"2026-07-05T06:50:59Z","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/2309.07598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Non-autoregressive (non-AR) sequence-to-seqeunce (seq2seq) models for voice conversion (VC) is attractive in its ability to effectively model the temporal structure while enjoying boosted intelligibility and fast inference thanks to non-AR modeling. However, the dependency of current non-AR seq2seq VC models on ground truth durations extracted from an external AR model greatly limits its generalization ability to smaller training datasets. In this paper, we first demonstrate the above-mentioned problem by varying the training data size. Then, we present AAS-VC, a non-AR seq2seq VC model based ","authors_text":"Kazuhiro Kobayashi, Tomoki Toda, Wen-Chin Huang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T10:59:29Z","title":"AAS-VC: On the Generalization Ability of Automatic Alignment Search based Non-autoregressive Sequence-to-sequence Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07598","kind":"arxiv","version":2},"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":"sha256:6a20e249b499c1a5b4754e1f52e3402c455ba98d317781ae7d9d143f64d157db","target":"record","created_at":"2026-07-05T06:50:59Z","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":"aaaffc114568f88e973f749ff8c98351af5d8dccd1d68fa238733d01255ebc67","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T10:59:29Z","title_canon_sha256":"74945a9cec14847d7ea91227d76528403843ead517aeb493680e4ecfedabd1a0"},"schema_version":"1.0","source":{"id":"2309.07598","kind":"arxiv","version":2}},"canonical_sha256":"b5389d43dae50b1d19612c2524e6958e67124483cbcbd5ac7fa439e38949ad95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5389d43dae50b1d19612c2524e6958e67124483cbcbd5ac7fa439e38949ad95","first_computed_at":"2026-07-05T06:50:59.130786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:59.130786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2EH3tJ4bOGcyDCLhbLv6CaohgTaE/Y6N2A0zNV5K2off7+NEqmLBOI73qmMpSZxiTLytSsy0Ju3U5lzVPgaPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:59.131374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07598","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a20e249b499c1a5b4754e1f52e3402c455ba98d317781ae7d9d143f64d157db","sha256:0efe949978226e8b9fdccfd2ee0c45267094ad3f0e9368cf9c437b382a2d55d3"],"state_sha256":"5f2f9016ccc96afa7bb1e382ac836c2e722b59d9061f5ba21bbee5e2b5eefc53"}