{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HV3BQWGYKWGF7S732YJTARFM3V","short_pith_number":"pith:HV3BQWGY","schema_version":"1.0","canonical_sha256":"3d761858d8558c5fcbfbd6133044acdd5e015bf04bcab2405966852e211bce7b","source":{"kind":"arxiv","id":"2012.14039","version":1},"attestation_state":"computed","paper":{"title":"Building Multi lingual TTS using Cross Lingual Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kenji Nagamatsu, Qinghua Sun","submitted_at":"2020-12-28T00:28:14Z","abstract_excerpt":"In this paper we propose a new cross-lingual Voice Conversion (VC) approach which can generate all speech parameters (MCEP, LF0, BAP) from one DNN model using PPGs (Phonetic PosteriorGrams) extracted from inputted speech using several ASR acoustic models. Using the proposed VC method, we tried three different approaches to build a multilingual TTS system without recording a multilingual speech corpus. A listening test was carried out to evaluate both speech quality (naturalness) and voice similarity between converted speech and target speech. The results show that Approach 1 achieved the highe"},"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":"2012.14039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-12-28T00:28:14Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0d37c1d8a5990aacf05be2e581b72f88facb2799f153cd3b41f048effa4baa21","abstract_canon_sha256":"d7978fb49ccd406071f68546561c776b970cf060da6d707c4db47ab6b9f83b0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:15.066868Z","signature_b64":"NNfTarIayC/DHtd250cXI1MJoHkkJiSjpexuffX4nT+9RwFluqJo0WubUUUwzbXOwkp8l6heHslRqxO5I2ALCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d761858d8558c5fcbfbd6133044acdd5e015bf04bcab2405966852e211bce7b","last_reissued_at":"2026-07-05T02:02:15.066457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:15.066457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Multi lingual TTS using Cross Lingual Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kenji Nagamatsu, Qinghua Sun","submitted_at":"2020-12-28T00:28:14Z","abstract_excerpt":"In this paper we propose a new cross-lingual Voice Conversion (VC) approach which can generate all speech parameters (MCEP, LF0, BAP) from one DNN model using PPGs (Phonetic PosteriorGrams) extracted from inputted speech using several ASR acoustic models. Using the proposed VC method, we tried three different approaches to build a multilingual TTS system without recording a multilingual speech corpus. A listening test was carried out to evaluate both speech quality (naturalness) and voice similarity between converted speech and target speech. The results show that Approach 1 achieved the highe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.14039","kind":"arxiv","version":1},"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/2012.14039/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":"2012.14039","created_at":"2026-07-05T02:02:15.066511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.14039v1","created_at":"2026-07-05T02:02:15.066511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.14039","created_at":"2026-07-05T02:02:15.066511+00:00"},{"alias_kind":"pith_short_12","alias_value":"HV3BQWGYKWGF","created_at":"2026-07-05T02:02:15.066511+00:00"},{"alias_kind":"pith_short_16","alias_value":"HV3BQWGYKWGF7S73","created_at":"2026-07-05T02:02:15.066511+00:00"},{"alias_kind":"pith_short_8","alias_value":"HV3BQWGY","created_at":"2026-07-05T02:02:15.066511+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/HV3BQWGYKWGF7S732YJTARFM3V","json":"https://pith.science/pith/HV3BQWGYKWGF7S732YJTARFM3V.json","graph_json":"https://pith.science/api/pith-number/HV3BQWGYKWGF7S732YJTARFM3V/graph.json","events_json":"https://pith.science/api/pith-number/HV3BQWGYKWGF7S732YJTARFM3V/events.json","paper":"https://pith.science/paper/HV3BQWGY"},"agent_actions":{"view_html":"https://pith.science/pith/HV3BQWGYKWGF7S732YJTARFM3V","download_json":"https://pith.science/pith/HV3BQWGYKWGF7S732YJTARFM3V.json","view_paper":"https://pith.science/paper/HV3BQWGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.14039&json=true","fetch_graph":"https://pith.science/api/pith-number/HV3BQWGYKWGF7S732YJTARFM3V/graph.json","fetch_events":"https://pith.science/api/pith-number/HV3BQWGYKWGF7S732YJTARFM3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HV3BQWGYKWGF7S732YJTARFM3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HV3BQWGYKWGF7S732YJTARFM3V/action/storage_attestation","attest_author":"https://pith.science/pith/HV3BQWGYKWGF7S732YJTARFM3V/action/author_attestation","sign_citation":"https://pith.science/pith/HV3BQWGYKWGF7S732YJTARFM3V/action/citation_signature","submit_replication":"https://pith.science/pith/HV3BQWGYKWGF7S732YJTARFM3V/action/replication_record"}},"created_at":"2026-07-05T02:02:15.066511+00:00","updated_at":"2026-07-05T02:02:15.066511+00:00"}