{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DI3ROMSL6IG4GVII4LNJ5VO3VJ","short_pith_number":"pith:DI3ROMSL","canonical_record":{"source":{"id":"2309.11977","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-21T11:22:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1eb0c2adb49b75537db599527142546780da68517ac68545e589a022c550a64b","abstract_canon_sha256":"3d5ae4b6a2f7e59470d2fbd83af3ec06d5888cbd252bad6ea7f17913a23c2eff"},"schema_version":"1.0"},"canonical_sha256":"1a3717324bf20dc35508e2da9ed5dbaa4d43159d2d02f0415e2daf7fbde09706","source":{"kind":"arxiv","id":"2309.11977","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11977","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11977v3","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11977","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"pith_short_12","alias_value":"DI3ROMSL6IG4","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"pith_short_16","alias_value":"DI3ROMSL6IG4GVII","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"pith_short_8","alias_value":"DI3ROMSL","created_at":"2026-07-05T08:05:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DI3ROMSL6IG4GVII4LNJ5VO3VJ","target":"record","payload":{"canonical_record":{"source":{"id":"2309.11977","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-21T11:22:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1eb0c2adb49b75537db599527142546780da68517ac68545e589a022c550a64b","abstract_canon_sha256":"3d5ae4b6a2f7e59470d2fbd83af3ec06d5888cbd252bad6ea7f17913a23c2eff"},"schema_version":"1.0"},"canonical_sha256":"1a3717324bf20dc35508e2da9ed5dbaa4d43159d2d02f0415e2daf7fbde09706","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:50.553420Z","signature_b64":"a/RRad8XgQRpxnN49DWLVV5NDtWhJFzDolO4bQ70/XagH6NpALQbMsn7vy9SAUKoZQ+EjvHbSuwBOsAQjcuhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a3717324bf20dc35508e2da9ed5dbaa4d43159d2d02f0415e2daf7fbde09706","last_reissued_at":"2026-07-05T08:05:50.553065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:50.553065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.11977","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lbHL92k6Au3ZPsf6ww/qq1LrjKYx2Ltr71XFkrulajx43mcUCKPX2zGZk3bPszU/ekUUmZTiZs3uIpw1hwI2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T22:18:52.592841Z"},"content_sha256":"34e649673834e099831bcd07d4de34b1957752f1d7d21ad50d628deb62e204e2","schema_version":"1.0","event_id":"sha256:34e649673834e099831bcd07d4de34b1957752f1d7d21ad50d628deb62e204e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DI3ROMSL6IG4GVII4LNJ5VO3VJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dan Luo, Helen Meng, Liyang Chen, Shiyin Kang, Shun Lei, Tao Jiang, Xixin Wu, Yahui Zhou, Yixuan Zhou, Yuxing Han, Zhiyong Wu","submitted_at":"2023-09-21T11:22:22Z","abstract_excerpt":"Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker's voice without adaptation parameters. By quantizing speech waveform into discrete acoustic tokens and modeling these tokens with the language model, recent language model-based TTS models show zero-shot speaker adaptation capabilities with only a 3-second acoustic prompt of an unseen speaker. However, they are limited by the length of the acoustic prompt, which makes it difficult to clone personal speaking style. In this paper, we propose a novel zero-shot TTS model with the multi-scale acoustic prompts based on a neura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11977","kind":"arxiv","version":3},"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/2309.11977/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":"2026-07-05T08:05:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BvJfS7kbdDi4GbtMR9KGXRSY7p6MchEmQkDtbfVCgdl4pEw7/uopNHRwj5+MCG4FYr2iTCmxOmHJbxQEwaleAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T22:18:52.593217Z"},"content_sha256":"8b9bbf4439c9bd1b6169369c154494cdbf0189b262d38fc7af9dbfed2d4dfa2c","schema_version":"1.0","event_id":"sha256:8b9bbf4439c9bd1b6169369c154494cdbf0189b262d38fc7af9dbfed2d4dfa2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DI3ROMSL6IG4GVII4LNJ5VO3VJ/bundle.json","state_url":"https://pith.science/pith/DI3ROMSL6IG4GVII4LNJ5VO3VJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DI3ROMSL6IG4GVII4LNJ5VO3VJ/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":"2026-07-09T22:18:52Z","links":{"resolver":"https://pith.science/pith/DI3ROMSL6IG4GVII4LNJ5VO3VJ","bundle":"https://pith.science/pith/DI3ROMSL6IG4GVII4LNJ5VO3VJ/bundle.json","state":"https://pith.science/pith/DI3ROMSL6IG4GVII4LNJ5VO3VJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DI3ROMSL6IG4GVII4LNJ5VO3VJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DI3ROMSL6IG4GVII4LNJ5VO3VJ","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":"3d5ae4b6a2f7e59470d2fbd83af3ec06d5888cbd252bad6ea7f17913a23c2eff","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-21T11:22:22Z","title_canon_sha256":"1eb0c2adb49b75537db599527142546780da68517ac68545e589a022c550a64b"},"schema_version":"1.0","source":{"id":"2309.11977","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11977","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11977v3","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11977","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"pith_short_12","alias_value":"DI3ROMSL6IG4","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"pith_short_16","alias_value":"DI3ROMSL6IG4GVII","created_at":"2026-07-05T08:05:50Z"},{"alias_kind":"pith_short_8","alias_value":"DI3ROMSL","created_at":"2026-07-05T08:05:50Z"}],"graph_snapshots":[{"event_id":"sha256:8b9bbf4439c9bd1b6169369c154494cdbf0189b262d38fc7af9dbfed2d4dfa2c","target":"graph","created_at":"2026-07-05T08:05:50Z","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/2309.11977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker's voice without adaptation parameters. By quantizing speech waveform into discrete acoustic tokens and modeling these tokens with the language model, recent language model-based TTS models show zero-shot speaker adaptation capabilities with only a 3-second acoustic prompt of an unseen speaker. However, they are limited by the length of the acoustic prompt, which makes it difficult to clone personal speaking style. In this paper, we propose a novel zero-shot TTS model with the multi-scale acoustic prompts based on a neura","authors_text":"Dan Luo, Helen Meng, Liyang Chen, Shiyin Kang, Shun Lei, Tao Jiang, Xixin Wu, Yahui Zhou, Yixuan Zhou, Yuxing Han, Zhiyong Wu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-21T11:22:22Z","title":"Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11977","kind":"arxiv","version":3},"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":"sha256:34e649673834e099831bcd07d4de34b1957752f1d7d21ad50d628deb62e204e2","target":"record","created_at":"2026-07-05T08:05:50Z","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":"3d5ae4b6a2f7e59470d2fbd83af3ec06d5888cbd252bad6ea7f17913a23c2eff","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-21T11:22:22Z","title_canon_sha256":"1eb0c2adb49b75537db599527142546780da68517ac68545e589a022c550a64b"},"schema_version":"1.0","source":{"id":"2309.11977","kind":"arxiv","version":3}},"canonical_sha256":"1a3717324bf20dc35508e2da9ed5dbaa4d43159d2d02f0415e2daf7fbde09706","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a3717324bf20dc35508e2da9ed5dbaa4d43159d2d02f0415e2daf7fbde09706","first_computed_at":"2026-07-05T08:05:50.553065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:50.553065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a/RRad8XgQRpxnN49DWLVV5NDtWhJFzDolO4bQ70/XagH6NpALQbMsn7vy9SAUKoZQ+EjvHbSuwBOsAQjcuhDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:50.553420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.11977","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34e649673834e099831bcd07d4de34b1957752f1d7d21ad50d628deb62e204e2","sha256:8b9bbf4439c9bd1b6169369c154494cdbf0189b262d38fc7af9dbfed2d4dfa2c"],"state_sha256":"49e5454ea89985ef5047d68ceb687c6bf2d0a074e9265f9d8febc534858b228e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I3ZBv6sOgi2d1hQuj2XHtk2iCNz0rsTFXpsYRnbalY9K7z9/B4EwDBYzdBuDCM63JGio6l0OzriCRLGbvU0rCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T22:18:52.595785Z","bundle_sha256":"fb1e11ca44564c1b0b93f7d45c994b03ff1c833a1887c845fa99baf806b90a8b"}}