{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WU4J2Q624UFR2GLBFQSSJZUVRZ","short_pith_number":"pith:WU4J2Q62","schema_version":"1.0","canonical_sha256":"b5389d43dae50b1d19612c2524e6958e67124483cbcbd5ac7fa439e38949ad95","source":{"kind":"arxiv","id":"2309.07598","version":2},"attestation_state":"computed","paper":{"title":"AAS-VC: On the Generalization Ability of Automatic Alignment Search based Non-autoregressive Sequence-to-sequence Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kazuhiro Kobayashi, Tomoki Toda, Wen-Chin Huang","submitted_at":"2023-09-14T10:59:29Z","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 "},"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":"2309.07598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T10:59:29Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"74945a9cec14847d7ea91227d76528403843ead517aeb493680e4ecfedabd1a0","abstract_canon_sha256":"aaaffc114568f88e973f749ff8c98351af5d8dccd1d68fa238733d01255ebc67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:59.131374Z","signature_b64":"2EH3tJ4bOGcyDCLhbLv6CaohgTaE/Y6N2A0zNV5K2off7+NEqmLBOI73qmMpSZxiTLytSsy0Ju3U5lzVPgaPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5389d43dae50b1d19612c2524e6958e67124483cbcbd5ac7fa439e38949ad95","last_reissued_at":"2026-07-05T06:50:59.130786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:59.130786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AAS-VC: On the Generalization Ability of Automatic Alignment Search based Non-autoregressive Sequence-to-sequence Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kazuhiro Kobayashi, Tomoki Toda, Wen-Chin Huang","submitted_at":"2023-09-14T10:59:29Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07598","kind":"arxiv","version":2},"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/2309.07598/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":"2309.07598","created_at":"2026-07-05T06:50:59.130838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07598v2","created_at":"2026-07-05T06:50:59.130838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07598","created_at":"2026-07-05T06:50:59.130838+00:00"},{"alias_kind":"pith_short_12","alias_value":"WU4J2Q624UFR","created_at":"2026-07-05T06:50:59.130838+00:00"},{"alias_kind":"pith_short_16","alias_value":"WU4J2Q624UFR2GLB","created_at":"2026-07-05T06:50:59.130838+00:00"},{"alias_kind":"pith_short_8","alias_value":"WU4J2Q62","created_at":"2026-07-05T06:50:59.130838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24304","citing_title":"A Perception-Based L2 Speech Intelligibility Indicator: Leveraging a Rater's Shadowing and Sequence-to-sequence Voice Conversion","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WU4J2Q624UFR2GLBFQSSJZUVRZ","json":"https://pith.science/pith/WU4J2Q624UFR2GLBFQSSJZUVRZ.json","graph_json":"https://pith.science/api/pith-number/WU4J2Q624UFR2GLBFQSSJZUVRZ/graph.json","events_json":"https://pith.science/api/pith-number/WU4J2Q624UFR2GLBFQSSJZUVRZ/events.json","paper":"https://pith.science/paper/WU4J2Q62"},"agent_actions":{"view_html":"https://pith.science/pith/WU4J2Q624UFR2GLBFQSSJZUVRZ","download_json":"https://pith.science/pith/WU4J2Q624UFR2GLBFQSSJZUVRZ.json","view_paper":"https://pith.science/paper/WU4J2Q62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07598&json=true","fetch_graph":"https://pith.science/api/pith-number/WU4J2Q624UFR2GLBFQSSJZUVRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WU4J2Q624UFR2GLBFQSSJZUVRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WU4J2Q624UFR2GLBFQSSJZUVRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WU4J2Q624UFR2GLBFQSSJZUVRZ/action/storage_attestation","attest_author":"https://pith.science/pith/WU4J2Q624UFR2GLBFQSSJZUVRZ/action/author_attestation","sign_citation":"https://pith.science/pith/WU4J2Q624UFR2GLBFQSSJZUVRZ/action/citation_signature","submit_replication":"https://pith.science/pith/WU4J2Q624UFR2GLBFQSSJZUVRZ/action/replication_record"}},"created_at":"2026-07-05T06:50:59.130838+00:00","updated_at":"2026-07-05T06:50:59.130838+00:00"}