{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HBR3KDBXV73A362LXIEJTKMXL2","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":"248c3b05edc486f47aa68869784af765edeaa2f871f80f8205614d202b0a4d0a","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-28T01:36:31Z","title_canon_sha256":"189c138ae6a9eae011839bf68345f0c499e74ca29aef2d4f308faba51b3c802b"},"schema_version":"1.0","source":{"id":"1905.11563","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11563","created_at":"2026-07-05T00:57:43Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11563v3","created_at":"2026-07-05T00:57:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11563","created_at":"2026-07-05T00:57:43Z"},{"alias_kind":"pith_short_12","alias_value":"HBR3KDBXV73A","created_at":"2026-07-05T00:57:43Z"},{"alias_kind":"pith_short_16","alias_value":"HBR3KDBXV73A362L","created_at":"2026-07-05T00:57:43Z"},{"alias_kind":"pith_short_8","alias_value":"HBR3KDBX","created_at":"2026-07-05T00:57:43Z"}],"graph_snapshots":[{"event_id":"sha256:a303aa19cab11b43fa85737de3e1303b7c39eb0f3685718138a5e9ad33bf61ea","target":"graph","created_at":"2026-07-05T00:57:43Z","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/1905.11563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an unsupervised end-to-end training scheme where we discover discrete subword units from speech without using any labels. The discrete subword units are learned under an ASR-TTS autoencoder reconstruction setting, where an ASR-Encoder is trained to discover a set of common linguistic units given a variety of speakers, and a TTS-Decoder trained to project the discovered units back to the designated speech. We propose a discrete encoding method, Multilabel-Binary Vectors (MBV), to make the ASR-TTS autoencoder differentiable. We found that the proposed encoding method offers automatic ","authors_text":"Andy T. Liu, Hung-yi Lee, Po-chun Hsu","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-28T01:36:31Z","title":"Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11563","kind":"arxiv","version":3},"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":"sha256:80eee7db5ec6acd11546b3c665217d1dd1dfeabd299982acb38867106b20b7a2","target":"record","created_at":"2026-07-05T00:57:43Z","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":"248c3b05edc486f47aa68869784af765edeaa2f871f80f8205614d202b0a4d0a","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-28T01:36:31Z","title_canon_sha256":"189c138ae6a9eae011839bf68345f0c499e74ca29aef2d4f308faba51b3c802b"},"schema_version":"1.0","source":{"id":"1905.11563","kind":"arxiv","version":3}},"canonical_sha256":"3863b50c37aff60dfb4bba0899a9975e829bc8c76e4e1220aabb771fa9e9e7a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3863b50c37aff60dfb4bba0899a9975e829bc8c76e4e1220aabb771fa9e9e7a6","first_computed_at":"2026-07-05T00:57:43.918569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:57:43.918569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O8syT10GuvE3SMP7FnlssWbzVvw57xZnjNnfMYlbGGjzx2Fz8hdHEQzL8/rWoC1xG12RSh+f38vvuXZJVhGOBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:57:43.919153Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11563","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80eee7db5ec6acd11546b3c665217d1dd1dfeabd299982acb38867106b20b7a2","sha256:a303aa19cab11b43fa85737de3e1303b7c39eb0f3685718138a5e9ad33bf61ea"],"state_sha256":"2bfe538a9bdbf93573a7e36c93b3603a825bc7b6d1a7a4125f79b6c474ad6021"}