{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IQTYFOANPZNBAKFIVGQ46XNPAN","short_pith_number":"pith:IQTYFOAN","schema_version":"1.0","canonical_sha256":"442782b80d7e5a1028a8a9a1cf5daf0346aa1cb51b9a73bfaf79bcd241e98bf3","source":{"kind":"arxiv","id":"2004.04972","version":1},"attestation_state":"computed","paper":{"title":"Generating Multilingual Voices Using Speaker Space Translation Based on Bilingual Speaker Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alistair Conkie, Erik Marchi, Soumi Maiti","submitted_at":"2020-04-10T10:01:53Z","abstract_excerpt":"We present progress towards bilingual Text-to-Speech which is able to transform a monolingual voice to speak a second language while preserving speaker voice quality. We demonstrate that a bilingual speaker embedding space contains a separate distribution for each language and that a simple transform in speaker space generated by the speaker embedding can be used to control the degree of accent of a synthetic voice in a language. The same transform can be applied even to monolingual speakers.\n  In our experiments speaker data from an English-Spanish (Mexican) bilingual speaker was used, and th"},"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":"2004.04972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-10T10:01:53Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"ead78e03c79cbc3b38206a3fa9066f0c98d07197ccf0db58c6c72213b85733d8","abstract_canon_sha256":"e205690b97eadc9d14a05d5f3f23f6755c1b8b88f4a9fd2cec40792711a7c465"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:24.271344Z","signature_b64":"PpxghJkQBuCpGFZUmn0GpnF3PYkgZpzD9fiNCnCYOUS8P1E0R+yET7fls7b+cHehnlzsAHZ6AI4T3mpB9df2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"442782b80d7e5a1028a8a9a1cf5daf0346aa1cb51b9a73bfaf79bcd241e98bf3","last_reissued_at":"2026-07-05T00:54:24.270769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:24.270769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Multilingual Voices Using Speaker Space Translation Based on Bilingual Speaker Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alistair Conkie, Erik Marchi, Soumi Maiti","submitted_at":"2020-04-10T10:01:53Z","abstract_excerpt":"We present progress towards bilingual Text-to-Speech which is able to transform a monolingual voice to speak a second language while preserving speaker voice quality. We demonstrate that a bilingual speaker embedding space contains a separate distribution for each language and that a simple transform in speaker space generated by the speaker embedding can be used to control the degree of accent of a synthetic voice in a language. The same transform can be applied even to monolingual speakers.\n  In our experiments speaker data from an English-Spanish (Mexican) bilingual speaker was used, and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.04972","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/2004.04972/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":"2004.04972","created_at":"2026-07-05T00:54:24.270831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.04972v1","created_at":"2026-07-05T00:54:24.270831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04972","created_at":"2026-07-05T00:54:24.270831+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQTYFOANPZNB","created_at":"2026-07-05T00:54:24.270831+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQTYFOANPZNBAKFI","created_at":"2026-07-05T00:54:24.270831+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQTYFOAN","created_at":"2026-07-05T00:54:24.270831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02083","citing_title":"LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQTYFOANPZNBAKFIVGQ46XNPAN","json":"https://pith.science/pith/IQTYFOANPZNBAKFIVGQ46XNPAN.json","graph_json":"https://pith.science/api/pith-number/IQTYFOANPZNBAKFIVGQ46XNPAN/graph.json","events_json":"https://pith.science/api/pith-number/IQTYFOANPZNBAKFIVGQ46XNPAN/events.json","paper":"https://pith.science/paper/IQTYFOAN"},"agent_actions":{"view_html":"https://pith.science/pith/IQTYFOANPZNBAKFIVGQ46XNPAN","download_json":"https://pith.science/pith/IQTYFOANPZNBAKFIVGQ46XNPAN.json","view_paper":"https://pith.science/paper/IQTYFOAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.04972&json=true","fetch_graph":"https://pith.science/api/pith-number/IQTYFOANPZNBAKFIVGQ46XNPAN/graph.json","fetch_events":"https://pith.science/api/pith-number/IQTYFOANPZNBAKFIVGQ46XNPAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQTYFOANPZNBAKFIVGQ46XNPAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQTYFOANPZNBAKFIVGQ46XNPAN/action/storage_attestation","attest_author":"https://pith.science/pith/IQTYFOANPZNBAKFIVGQ46XNPAN/action/author_attestation","sign_citation":"https://pith.science/pith/IQTYFOANPZNBAKFIVGQ46XNPAN/action/citation_signature","submit_replication":"https://pith.science/pith/IQTYFOANPZNBAKFIVGQ46XNPAN/action/replication_record"}},"created_at":"2026-07-05T00:54:24.270831+00:00","updated_at":"2026-07-05T00:54:24.270831+00:00"}