{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NWJMGVC5RW2ST3IEDNG5IRZUDF","short_pith_number":"pith:NWJMGVC5","schema_version":"1.0","canonical_sha256":"6d92c3545d8db529ed041b4dd447341964b90d270c6651a055587ccfff4d8d11","source":{"kind":"arxiv","id":"2401.13921","version":1},"attestation_state":"computed","paper":{"title":"Intelli-Z: Toward Intelligible Zero-Shot TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bongwan Kim, Jaesam Yoon, Sunghee Jung, Won Jang","submitted_at":"2024-01-25T03:37:23Z","abstract_excerpt":"Although numerous recent studies have suggested new frameworks for zero-shot TTS using large-scale, real-world data, studies that focus on the intelligibility of zero-shot TTS are relatively scarce. Zero-shot TTS demands additional efforts to ensure clear pronunciation and speech quality due to its inherent requirement of replacing a core parameter (speaker embedding or acoustic prompt) with a new one at the inference stage. In this study, we propose a zero-shot TTS model focused on intelligibility, which we refer to as Intelli-Z. Intelli-Z learns speaker embeddings by using multi-speaker TTS "},"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":"2401.13921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-25T03:37:23Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"caec2eda84584a0f94150d5f0ced442634191863c441ae66d6b9a77879db9a6b","abstract_canon_sha256":"0e2737169b87264d34ad190a6d8ee18f1044c7d80a8b9ee3648498d55d0370cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:13.232606Z","signature_b64":"Bu58le87Z2SBM6ZtDZpTXgYJE6AV7Oi/lavW1LxhBwNkzSepFdo1nwUjuS4LshHxRuxaNJ5iZbX9/P+C+dSxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d92c3545d8db529ed041b4dd447341964b90d270c6651a055587ccfff4d8d11","last_reissued_at":"2026-07-05T07:39:13.231641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:13.231641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intelli-Z: Toward Intelligible Zero-Shot TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bongwan Kim, Jaesam Yoon, Sunghee Jung, Won Jang","submitted_at":"2024-01-25T03:37:23Z","abstract_excerpt":"Although numerous recent studies have suggested new frameworks for zero-shot TTS using large-scale, real-world data, studies that focus on the intelligibility of zero-shot TTS are relatively scarce. Zero-shot TTS demands additional efforts to ensure clear pronunciation and speech quality due to its inherent requirement of replacing a core parameter (speaker embedding or acoustic prompt) with a new one at the inference stage. In this study, we propose a zero-shot TTS model focused on intelligibility, which we refer to as Intelli-Z. Intelli-Z learns speaker embeddings by using multi-speaker TTS "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13921","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/2401.13921/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":"2401.13921","created_at":"2026-07-05T07:39:13.232113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13921v1","created_at":"2026-07-05T07:39:13.232113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13921","created_at":"2026-07-05T07:39:13.232113+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWJMGVC5RW2S","created_at":"2026-07-05T07:39:13.232113+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWJMGVC5RW2ST3IE","created_at":"2026-07-05T07:39:13.232113+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWJMGVC5","created_at":"2026-07-05T07:39:13.232113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19384","citing_title":"GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF","json":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF.json","graph_json":"https://pith.science/api/pith-number/NWJMGVC5RW2ST3IEDNG5IRZUDF/graph.json","events_json":"https://pith.science/api/pith-number/NWJMGVC5RW2ST3IEDNG5IRZUDF/events.json","paper":"https://pith.science/paper/NWJMGVC5"},"agent_actions":{"view_html":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF","download_json":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF.json","view_paper":"https://pith.science/paper/NWJMGVC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13921&json=true","fetch_graph":"https://pith.science/api/pith-number/NWJMGVC5RW2ST3IEDNG5IRZUDF/graph.json","fetch_events":"https://pith.science/api/pith-number/NWJMGVC5RW2ST3IEDNG5IRZUDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/action/storage_attestation","attest_author":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/action/author_attestation","sign_citation":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/action/citation_signature","submit_replication":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/action/replication_record"}},"created_at":"2026-07-05T07:39:13.232113+00:00","updated_at":"2026-07-05T07:39:13.232113+00:00"}