{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HBR3KDBXV73A362LXIEJTKMXL2","short_pith_number":"pith:HBR3KDBX","schema_version":"1.0","canonical_sha256":"3863b50c37aff60dfb4bba0899a9975e829bc8c76e4e1220aabb771fa9e9e7a6","source":{"kind":"arxiv","id":"1905.11563","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andy T. Liu, Hung-yi Lee, Po-chun Hsu","submitted_at":"2019-05-28T01:36:31Z","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 "},"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":"1905.11563","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-28T01:36:31Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"189c138ae6a9eae011839bf68345f0c499e74ca29aef2d4f308faba51b3c802b","abstract_canon_sha256":"248c3b05edc486f47aa68869784af765edeaa2f871f80f8205614d202b0a4d0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:43.919153Z","signature_b64":"O8syT10GuvE3SMP7FnlssWbzVvw57xZnjNnfMYlbGGjzx2Fz8hdHEQzL8/rWoC1xG12RSh+f38vvuXZJVhGOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3863b50c37aff60dfb4bba0899a9975e829bc8c76e4e1220aabb771fa9e9e7a6","last_reissued_at":"2026-07-05T00:57:43.918569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:43.918569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andy T. Liu, Hung-yi Lee, Po-chun Hsu","submitted_at":"2019-05-28T01:36:31Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11563","kind":"arxiv","version":3},"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/1905.11563/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":"1905.11563","created_at":"2026-07-05T00:57:43.918763+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11563v3","created_at":"2026-07-05T00:57:43.918763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11563","created_at":"2026-07-05T00:57:43.918763+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBR3KDBXV73A","created_at":"2026-07-05T00:57:43.918763+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBR3KDBXV73A362L","created_at":"2026-07-05T00:57:43.918763+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBR3KDBX","created_at":"2026-07-05T00:57:43.918763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07036","citing_title":"In This Environment, As That Speaker: A Text-Driven Framework for Multi-Attribute Speech Conversion","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBR3KDBXV73A362LXIEJTKMXL2","json":"https://pith.science/pith/HBR3KDBXV73A362LXIEJTKMXL2.json","graph_json":"https://pith.science/api/pith-number/HBR3KDBXV73A362LXIEJTKMXL2/graph.json","events_json":"https://pith.science/api/pith-number/HBR3KDBXV73A362LXIEJTKMXL2/events.json","paper":"https://pith.science/paper/HBR3KDBX"},"agent_actions":{"view_html":"https://pith.science/pith/HBR3KDBXV73A362LXIEJTKMXL2","download_json":"https://pith.science/pith/HBR3KDBXV73A362LXIEJTKMXL2.json","view_paper":"https://pith.science/paper/HBR3KDBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11563&json=true","fetch_graph":"https://pith.science/api/pith-number/HBR3KDBXV73A362LXIEJTKMXL2/graph.json","fetch_events":"https://pith.science/api/pith-number/HBR3KDBXV73A362LXIEJTKMXL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBR3KDBXV73A362LXIEJTKMXL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBR3KDBXV73A362LXIEJTKMXL2/action/storage_attestation","attest_author":"https://pith.science/pith/HBR3KDBXV73A362LXIEJTKMXL2/action/author_attestation","sign_citation":"https://pith.science/pith/HBR3KDBXV73A362LXIEJTKMXL2/action/citation_signature","submit_replication":"https://pith.science/pith/HBR3KDBXV73A362LXIEJTKMXL2/action/replication_record"}},"created_at":"2026-07-05T00:57:43.918763+00:00","updated_at":"2026-07-05T00:57:43.918763+00:00"}