{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5YBVB564HDMGGVJEROWQ3TL7BL","short_pith_number":"pith:5YBVB564","canonical_record":{"source":{"id":"2412.06602","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T15:50:25Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"0bda23c3b911e2395401ce8081eb9cbe6fe545e3d1e5cfd16dc366da0e034319","abstract_canon_sha256":"12a0b75c44d67e794e83a153a14fc3187e8ac03a0b9473257a53972f2c42f173"},"schema_version":"1.0"},"canonical_sha256":"ee0350f7dc38d86355248bad0dcd7f0ad59c95317ef8c21bff9f6be8f92035fb","source":{"kind":"arxiv","id":"2412.06602","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06602","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06602v3","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06602","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"5YBVB564HDMG","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"5YBVB564HDMGGVJE","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"5YBVB564","created_at":"2026-07-05T11:58:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5YBVB564HDMGGVJEROWQ3TL7BL","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06602","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T15:50:25Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"0bda23c3b911e2395401ce8081eb9cbe6fe545e3d1e5cfd16dc366da0e034319","abstract_canon_sha256":"12a0b75c44d67e794e83a153a14fc3187e8ac03a0b9473257a53972f2c42f173"},"schema_version":"1.0"},"canonical_sha256":"ee0350f7dc38d86355248bad0dcd7f0ad59c95317ef8c21bff9f6be8f92035fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:22.609593Z","signature_b64":"/w9WRzjTAz2lD680B4SgSTKG1k7mjBtiNu8ghdryAV5Ne+wMjL/GbjIBL+qVQYoPgNsISSBfV73M54Hk0YeQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee0350f7dc38d86355248bad0dcd7f0ad59c95317ef8c21bff9f6be8f92035fb","last_reissued_at":"2026-07-05T11:58:22.609077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:22.609077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06602","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":"2026-07-05T11:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUu+n43qeuNZDSvZK4itJm8tquvf+yt8+xESDtLqaE2JDwQr5+Y7k1cAbTOdnuvJhiYROSjWNwROc+JdobKQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:52:14.462083Z"},"content_sha256":"3b5445768e9dd6be36c48960301f59eab0e49170aa708990ac5f8cf22b2a0f24","schema_version":"1.0","event_id":"sha256:3b5445768e9dd6be36c48960301f59eab0e49170aa708990ac5f8cf22b2a0f24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5YBVB564HDMGGVJEROWQ3TL7BL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Li Liu, Pengfei Zhang, Tianxin Xie, Wenwu Wang, Yan Rong","submitted_at":"2024-12-09T15:50:25Z","abstract_excerpt":"Text-to-speech (TTS) has advanced from generating natural-sounding speech to enabling fine-grained control over attributes like emotion, timbre, and style. Driven by rising industrial demand and breakthroughs in deep learning, e.g., diffusion and large language models (LLMs), controllable TTS has become a rapidly growing research area. This survey provides the first comprehensive review of controllable TTS methods, from traditional control techniques to emerging approaches using natural language prompts. We categorize model architectures, control strategies, and feature representations, while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06602","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/2412.06602/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":"2026-07-05T11:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTxtpdZ+cgHvR6wGoVt/Xtz9hT8Rj22Jbz4Xf6WTB/Ni0WeAU8KoS8ZoTxvalN1KcJZyCCOnaojuqq2BcuqSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:52:14.462632Z"},"content_sha256":"8616f19308969819e83a80e99d1c036dbebf64f7a982beefeb0abe79fb7f16ef","schema_version":"1.0","event_id":"sha256:8616f19308969819e83a80e99d1c036dbebf64f7a982beefeb0abe79fb7f16ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5YBVB564HDMGGVJEROWQ3TL7BL/bundle.json","state_url":"https://pith.science/pith/5YBVB564HDMGGVJEROWQ3TL7BL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5YBVB564HDMGGVJEROWQ3TL7BL/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":"2026-08-06T21:52:14Z","links":{"resolver":"https://pith.science/pith/5YBVB564HDMGGVJEROWQ3TL7BL","bundle":"https://pith.science/pith/5YBVB564HDMGGVJEROWQ3TL7BL/bundle.json","state":"https://pith.science/pith/5YBVB564HDMGGVJEROWQ3TL7BL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5YBVB564HDMGGVJEROWQ3TL7BL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5YBVB564HDMGGVJEROWQ3TL7BL","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":"12a0b75c44d67e794e83a153a14fc3187e8ac03a0b9473257a53972f2c42f173","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T15:50:25Z","title_canon_sha256":"0bda23c3b911e2395401ce8081eb9cbe6fe545e3d1e5cfd16dc366da0e034319"},"schema_version":"1.0","source":{"id":"2412.06602","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06602","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06602v3","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06602","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"5YBVB564HDMG","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"5YBVB564HDMGGVJE","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"5YBVB564","created_at":"2026-07-05T11:58:22Z"}],"graph_snapshots":[{"event_id":"sha256:8616f19308969819e83a80e99d1c036dbebf64f7a982beefeb0abe79fb7f16ef","target":"graph","created_at":"2026-07-05T11:58:22Z","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/2412.06602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-speech (TTS) has advanced from generating natural-sounding speech to enabling fine-grained control over attributes like emotion, timbre, and style. Driven by rising industrial demand and breakthroughs in deep learning, e.g., diffusion and large language models (LLMs), controllable TTS has become a rapidly growing research area. This survey provides the first comprehensive review of controllable TTS methods, from traditional control techniques to emerging approaches using natural language prompts. We categorize model architectures, control strategies, and feature representations, while ","authors_text":"Li Liu, Pengfei Zhang, Tianxin Xie, Wenwu Wang, Yan Rong","cross_cats":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T15:50:25Z","title":"Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06602","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":"sha256:3b5445768e9dd6be36c48960301f59eab0e49170aa708990ac5f8cf22b2a0f24","target":"record","created_at":"2026-07-05T11:58:22Z","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":"12a0b75c44d67e794e83a153a14fc3187e8ac03a0b9473257a53972f2c42f173","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T15:50:25Z","title_canon_sha256":"0bda23c3b911e2395401ce8081eb9cbe6fe545e3d1e5cfd16dc366da0e034319"},"schema_version":"1.0","source":{"id":"2412.06602","kind":"arxiv","version":3}},"canonical_sha256":"ee0350f7dc38d86355248bad0dcd7f0ad59c95317ef8c21bff9f6be8f92035fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee0350f7dc38d86355248bad0dcd7f0ad59c95317ef8c21bff9f6be8f92035fb","first_computed_at":"2026-07-05T11:58:22.609077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:22.609077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/w9WRzjTAz2lD680B4SgSTKG1k7mjBtiNu8ghdryAV5Ne+wMjL/GbjIBL+qVQYoPgNsISSBfV73M54Hk0YeQAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:22.609593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06602","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b5445768e9dd6be36c48960301f59eab0e49170aa708990ac5f8cf22b2a0f24","sha256:8616f19308969819e83a80e99d1c036dbebf64f7a982beefeb0abe79fb7f16ef"],"state_sha256":"08550fad42c1661d833fc4f12f2a085718343d5a5147f9e8ece3d90ba40e2b5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mli7QqVGgvSg4Mq6m0HCND4BYcfMF9xxsWfxmqUp0XzsTsvWBNNRI9UHoTpuRXbelAfQZzx26G2mR+3+zsuAAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:52:14.466360Z","bundle_sha256":"9b1ec2b78af2fb7737b12cdd8536cdc252c05de5fedf6a783d40e9005d85127d"}}