{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NWJMGVC5RW2ST3IEDNG5IRZUDF","short_pith_number":"pith:NWJMGVC5","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"},"canonical_sha256":"6d92c3545d8db529ed041b4dd447341964b90d270c6651a055587ccfff4d8d11","source":{"kind":"arxiv","id":"2401.13921","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13921","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13921v1","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13921","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"NWJMGVC5RW2S","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_16","alias_value":"NWJMGVC5RW2ST3IE","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_8","alias_value":"NWJMGVC5","created_at":"2026-07-05T07:39:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NWJMGVC5RW2ST3IEDNG5IRZUDF","target":"record","payload":{"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"},"canonical_sha256":"6d92c3545d8db529ed041b4dd447341964b90d270c6651a055587ccfff4d8d11","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"},"source_kind":"arxiv","source_id":"2401.13921","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XE/jDn21mH25rgKL1vtwz9wX4PY2Os+8psg70tqecwYqseTyoDlNyUicSc4eaeyOdT92VR63kx22saUJJ9pCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:35:24.915457Z"},"content_sha256":"73e7d9a6b4b42bc6946e593eb44c0c19bb2596cbba5126ad76f7801e1ea51c4d","schema_version":"1.0","event_id":"sha256:73e7d9a6b4b42bc6946e593eb44c0c19bb2596cbba5126ad76f7801e1ea51c4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NWJMGVC5RW2ST3IEDNG5IRZUDF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3I1NJQ5HcJnkvoNplNzGYOzZxsssKyRJmw3buHO26P9KNJ2y6hHvwRvvq92QD2B/X71OVoT077IKv8izI2wcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:35:24.916065Z"},"content_sha256":"844287b7c57e53926afa2c1af8b3cd5db56564f999c3106dd4658c20e41c2e9c","schema_version":"1.0","event_id":"sha256:844287b7c57e53926afa2c1af8b3cd5db56564f999c3106dd4658c20e41c2e9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/bundle.json","state_url":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T08:35:24Z","links":{"resolver":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF","bundle":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/bundle.json","state":"https://pith.science/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NWJMGVC5RW2ST3IEDNG5IRZUDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NWJMGVC5RW2ST3IEDNG5IRZUDF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0e2737169b87264d34ad190a6d8ee18f1044c7d80a8b9ee3648498d55d0370cd","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-25T03:37:23Z","title_canon_sha256":"caec2eda84584a0f94150d5f0ced442634191863c441ae66d6b9a77879db9a6b"},"schema_version":"1.0","source":{"id":"2401.13921","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13921","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13921v1","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13921","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"NWJMGVC5RW2S","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_16","alias_value":"NWJMGVC5RW2ST3IE","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_8","alias_value":"NWJMGVC5","created_at":"2026-07-05T07:39:13Z"}],"graph_snapshots":[{"event_id":"sha256:844287b7c57e53926afa2c1af8b3cd5db56564f999c3106dd4658c20e41c2e9c","target":"graph","created_at":"2026-07-05T07:39:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.13921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Bongwan Kim, Jaesam Yoon, Sunghee Jung, Won Jang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-25T03:37:23Z","title":"Intelli-Z: Toward Intelligible Zero-Shot TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13921","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:73e7d9a6b4b42bc6946e593eb44c0c19bb2596cbba5126ad76f7801e1ea51c4d","target":"record","created_at":"2026-07-05T07:39:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0e2737169b87264d34ad190a6d8ee18f1044c7d80a8b9ee3648498d55d0370cd","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-25T03:37:23Z","title_canon_sha256":"caec2eda84584a0f94150d5f0ced442634191863c441ae66d6b9a77879db9a6b"},"schema_version":"1.0","source":{"id":"2401.13921","kind":"arxiv","version":1}},"canonical_sha256":"6d92c3545d8db529ed041b4dd447341964b90d270c6651a055587ccfff4d8d11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d92c3545d8db529ed041b4dd447341964b90d270c6651a055587ccfff4d8d11","first_computed_at":"2026-07-05T07:39:13.231641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:13.231641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bu58le87Z2SBM6ZtDZpTXgYJE6AV7Oi/lavW1LxhBwNkzSepFdo1nwUjuS4LshHxRuxaNJ5iZbX9/P+C+dSxBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:13.232606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13921","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73e7d9a6b4b42bc6946e593eb44c0c19bb2596cbba5126ad76f7801e1ea51c4d","sha256:844287b7c57e53926afa2c1af8b3cd5db56564f999c3106dd4658c20e41c2e9c"],"state_sha256":"3467f0c7059c1f50581f9872fbd3f91569d48cb27dc6cdaec985f8496ffa6e92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rEPzPASjDm5QoILU/G/4eYsH6hdq9yfatWchipaivYmsBvpan319gTOHqfKburaLb31lelcGIxNofOXDOxobCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:35:24.922229Z","bundle_sha256":"ad6090768269fcfa5604e3792083dc5dca3791902671055b16e5f4beb4a32c4a"}}