{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BFWXKHAVDD42RFP64RQHCAJNTY","short_pith_number":"pith:BFWXKHAV","schema_version":"1.0","canonical_sha256":"096d751c1518f9a895fee46071012d9e031d69a076a6dd2d9a9d3121284d8c1c","source":{"kind":"arxiv","id":"2202.03125","version":1},"attestation_state":"computed","paper":{"title":"Building Synthetic Speaker Profiles in Text-to-Speech Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jie Pu, Oguz Elibol, Yixiong Meng","submitted_at":"2022-02-07T13:06:18Z","abstract_excerpt":"The diversity of speaker profiles in multi-speaker TTS systems is a crucial aspect of its performance, as it measures how many different speaker profiles TTS systems could possibly synthesize. However, this important aspect is often overlooked when building multi-speaker TTS systems and there is no established framework to evaluate this diversity. The reason behind is that most multi-speaker TTS systems are limited to generate speech signals with the same speaker profiles as its training data. They often use discrete speaker embedding vectors which have a one-to-one correspondence with individ"},"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":"2202.03125","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-02-07T13:06:18Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8d5d8e9b8c2dda354d643857718dd22897a4fbca98ebca6be8e099cde69034c8","abstract_canon_sha256":"0547f213f69f3a81257aa0292435cd71431c7760609a50102a0d3fb413951c17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:35.828463Z","signature_b64":"j/AqcBmNCXKAsWIq3yPqdMugDJdFc3SqXjGUq9kS0+iKbjIK69nyZU2mTnroFaCjRWKG75GhhrrQuj31KXN8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"096d751c1518f9a895fee46071012d9e031d69a076a6dd2d9a9d3121284d8c1c","last_reissued_at":"2026-07-05T03:54:35.828084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:35.828084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Synthetic Speaker Profiles in Text-to-Speech Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jie Pu, Oguz Elibol, Yixiong Meng","submitted_at":"2022-02-07T13:06:18Z","abstract_excerpt":"The diversity of speaker profiles in multi-speaker TTS systems is a crucial aspect of its performance, as it measures how many different speaker profiles TTS systems could possibly synthesize. However, this important aspect is often overlooked when building multi-speaker TTS systems and there is no established framework to evaluate this diversity. The reason behind is that most multi-speaker TTS systems are limited to generate speech signals with the same speaker profiles as its training data. They often use discrete speaker embedding vectors which have a one-to-one correspondence with individ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03125","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/2202.03125/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":"2202.03125","created_at":"2026-07-05T03:54:35.828138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03125v1","created_at":"2026-07-05T03:54:35.828138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03125","created_at":"2026-07-05T03:54:35.828138+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFWXKHAVDD42","created_at":"2026-07-05T03:54:35.828138+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFWXKHAVDD42RFP6","created_at":"2026-07-05T03:54:35.828138+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFWXKHAV","created_at":"2026-07-05T03:54:35.828138+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/BFWXKHAVDD42RFP64RQHCAJNTY","json":"https://pith.science/pith/BFWXKHAVDD42RFP64RQHCAJNTY.json","graph_json":"https://pith.science/api/pith-number/BFWXKHAVDD42RFP64RQHCAJNTY/graph.json","events_json":"https://pith.science/api/pith-number/BFWXKHAVDD42RFP64RQHCAJNTY/events.json","paper":"https://pith.science/paper/BFWXKHAV"},"agent_actions":{"view_html":"https://pith.science/pith/BFWXKHAVDD42RFP64RQHCAJNTY","download_json":"https://pith.science/pith/BFWXKHAVDD42RFP64RQHCAJNTY.json","view_paper":"https://pith.science/paper/BFWXKHAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03125&json=true","fetch_graph":"https://pith.science/api/pith-number/BFWXKHAVDD42RFP64RQHCAJNTY/graph.json","fetch_events":"https://pith.science/api/pith-number/BFWXKHAVDD42RFP64RQHCAJNTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFWXKHAVDD42RFP64RQHCAJNTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFWXKHAVDD42RFP64RQHCAJNTY/action/storage_attestation","attest_author":"https://pith.science/pith/BFWXKHAVDD42RFP64RQHCAJNTY/action/author_attestation","sign_citation":"https://pith.science/pith/BFWXKHAVDD42RFP64RQHCAJNTY/action/citation_signature","submit_replication":"https://pith.science/pith/BFWXKHAVDD42RFP64RQHCAJNTY/action/replication_record"}},"created_at":"2026-07-05T03:54:35.828138+00:00","updated_at":"2026-07-05T03:54:35.828138+00:00"}