{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CUBBO2GWNENROJBYEXPGJSRMQV","short_pith_number":"pith:CUBBO2GW","schema_version":"1.0","canonical_sha256":"15021768d6691b17243825de64ca2c8553edce2363871372dabc4ad67aab2aec","source":{"kind":"arxiv","id":"1905.11449","version":2},"attestation_state":"computed","paper":{"title":"VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andros Tjandra, Berrak Sisman, Haizhou Li, Mingyang Zhang, Sakriani Sakti, Satoshi Nakamura","submitted_at":"2019-05-27T18:59:54Z","abstract_excerpt":"We describe our submitted system for the ZeroSpeech Challenge 2019. The current challenge theme addresses the difficulty of constructing a speech synthesizer without any text or phonetic labels and requires a system that can (1) discover subword units in an unsupervised way, and (2) synthesize the speech with a target speaker's voice. Moreover, the system should also balance the discrimination score ABX, the bit-rate compression rate, and the naturalness and the intelligibility of the constructed voice. To tackle these problems and achieve the best trade-off, we utilize a vector quantized vari"},"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":"1905.11449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-27T18:59:54Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"3dcb24adb2eed6a9b5b7d21475c5844ea5c504fce4a5c654820b13074cf7a66b","abstract_canon_sha256":"531663a5976c1d231ef8df80a139df88a90ad4c4e947da6ab9a0751720df753b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:47.104845Z","signature_b64":"/6tgmLvIcxaHY5MfKk73s/MEgX+IZjv456Yqw8p52sRPDZQmr+Khy3si1rMJ7KEwrdLJYWCgKLo2rtc857X+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15021768d6691b17243825de64ca2c8553edce2363871372dabc4ad67aab2aec","last_reissued_at":"2026-05-17T23:44:47.104126Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:47.104126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andros Tjandra, Berrak Sisman, Haizhou Li, Mingyang Zhang, Sakriani Sakti, Satoshi Nakamura","submitted_at":"2019-05-27T18:59:54Z","abstract_excerpt":"We describe our submitted system for the ZeroSpeech Challenge 2019. The current challenge theme addresses the difficulty of constructing a speech synthesizer without any text or phonetic labels and requires a system that can (1) discover subword units in an unsupervised way, and (2) synthesize the speech with a target speaker's voice. Moreover, the system should also balance the discrimination score ABX, the bit-rate compression rate, and the naturalness and the intelligibility of the constructed voice. To tackle these problems and achieve the best trade-off, we utilize a vector quantized vari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11449","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":""},"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":"1905.11449","created_at":"2026-05-17T23:44:47.104230+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11449v2","created_at":"2026-05-17T23:44:47.104230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11449","created_at":"2026-05-17T23:44:47.104230+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUBBO2GWNENR","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUBBO2GWNENROJBY","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUBBO2GW","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUBBO2GWNENROJBYEXPGJSRMQV","json":"https://pith.science/pith/CUBBO2GWNENROJBYEXPGJSRMQV.json","graph_json":"https://pith.science/api/pith-number/CUBBO2GWNENROJBYEXPGJSRMQV/graph.json","events_json":"https://pith.science/api/pith-number/CUBBO2GWNENROJBYEXPGJSRMQV/events.json","paper":"https://pith.science/paper/CUBBO2GW"},"agent_actions":{"view_html":"https://pith.science/pith/CUBBO2GWNENROJBYEXPGJSRMQV","download_json":"https://pith.science/pith/CUBBO2GWNENROJBYEXPGJSRMQV.json","view_paper":"https://pith.science/paper/CUBBO2GW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11449&json=true","fetch_graph":"https://pith.science/api/pith-number/CUBBO2GWNENROJBYEXPGJSRMQV/graph.json","fetch_events":"https://pith.science/api/pith-number/CUBBO2GWNENROJBYEXPGJSRMQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUBBO2GWNENROJBYEXPGJSRMQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUBBO2GWNENROJBYEXPGJSRMQV/action/storage_attestation","attest_author":"https://pith.science/pith/CUBBO2GWNENROJBYEXPGJSRMQV/action/author_attestation","sign_citation":"https://pith.science/pith/CUBBO2GWNENROJBYEXPGJSRMQV/action/citation_signature","submit_replication":"https://pith.science/pith/CUBBO2GWNENROJBYEXPGJSRMQV/action/replication_record"}},"created_at":"2026-05-17T23:44:47.104230+00:00","updated_at":"2026-05-17T23:44:47.104230+00:00"}