{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:G3YM2GHJAJFXE2EXBFFEIQH5FM","short_pith_number":"pith:G3YM2GHJ","canonical_record":{"source":{"id":"2112.12743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-23T17:54:45Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"96804992504421cd89b7aa5b88601b1c8a36ef782a36c27c5c84b9eb43362321","abstract_canon_sha256":"b3d632ff93ee9f92e2fab962118457b2f8fc85fe658aa97843ae82a225d83e99"},"schema_version":"1.0"},"canonical_sha256":"36f0cd18e9024b726897094a4440fd2b30ca78b8cdc5e9fc3a9238f7a28d0f4c","source":{"kind":"arxiv","id":"2112.12743","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.12743","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2112.12743v1","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12743","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"G3YM2GHJAJFX","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"G3YM2GHJAJFXE2EX","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"G3YM2GHJ","created_at":"2026-07-05T03:43:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:G3YM2GHJAJFXE2EXBFFEIQH5FM","target":"record","payload":{"canonical_record":{"source":{"id":"2112.12743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-23T17:54:45Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"96804992504421cd89b7aa5b88601b1c8a36ef782a36c27c5c84b9eb43362321","abstract_canon_sha256":"b3d632ff93ee9f92e2fab962118457b2f8fc85fe658aa97843ae82a225d83e99"},"schema_version":"1.0"},"canonical_sha256":"36f0cd18e9024b726897094a4440fd2b30ca78b8cdc5e9fc3a9238f7a28d0f4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:30.812705Z","signature_b64":"Femrd33Ne7V2aSSrOtIA3JAgvozXODX3x+1lKDZsLsv9lOv3MgTqMR3wiGsdSBjm+bQUYQ360rWXtbO+UPKqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36f0cd18e9024b726897094a4440fd2b30ca78b8cdc5e9fc3a9238f7a28d0f4c","last_reissued_at":"2026-07-05T03:43:30.812262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:30.812262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.12743","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":"2026-07-05T03:43:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sP8IvSxSJl4d+Hk/TiOmbjk0PreJTsPQjMLSxyfgJDKwaFUReSgYtROeb9Hym5nOcYr+dPzZnSrr4SxJrTvOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:43:23.201240Z"},"content_sha256":"b5abf28a649a7376664f4e85056889a58493f05646ff1dc78f1fe59c2fd7e854","schema_version":"1.0","event_id":"sha256:b5abf28a649a7376664f4e85056889a58493f05646ff1dc78f1fe59c2fd7e854"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:G3YM2GHJAJFXE2EXBFFEIQH5FM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Guanglu Wan, Guoqiao Yu, Lei Xie, Qicong Xie, Tao Li, Xinsheng Wang, Zhichao Wang","submitted_at":"2021-12-23T17:54:45Z","abstract_excerpt":"In the existing cross-speaker style transfer task, a source speaker with multi-style recordings is necessary to provide the style for a target speaker. However, it is hard for one speaker to express all expected styles. In this paper, a more general task, which is to produce expressive speech by combining any styles and timbres from a multi-speaker corpus in which each speaker has a unique style, is proposed. To realize this task, a novel method is proposed. This method is a Tacotron2-based framework but with a fine-grained text-based prosody predicting module and a speaker identity controller"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12743","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/2112.12743/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":"2026-07-05T03:43:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HJuw1XQvFTf9NRA99t1ab6vsD0r1Rtt7azxPm5Lw12cIc1PpNFDWV7Hay2Mh187Ek5AlO9WIO1tW51PjQ3zXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:43:23.201779Z"},"content_sha256":"7882eed08123e9a5a8894ec46a2e7d038a8d6b7515fe404fa4cc3d8be0d0c305","schema_version":"1.0","event_id":"sha256:7882eed08123e9a5a8894ec46a2e7d038a8d6b7515fe404fa4cc3d8be0d0c305"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3YM2GHJAJFXE2EXBFFEIQH5FM/bundle.json","state_url":"https://pith.science/pith/G3YM2GHJAJFXE2EXBFFEIQH5FM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3YM2GHJAJFXE2EXBFFEIQH5FM/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":"2026-08-20T10:43:23Z","links":{"resolver":"https://pith.science/pith/G3YM2GHJAJFXE2EXBFFEIQH5FM","bundle":"https://pith.science/pith/G3YM2GHJAJFXE2EXBFFEIQH5FM/bundle.json","state":"https://pith.science/pith/G3YM2GHJAJFXE2EXBFFEIQH5FM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3YM2GHJAJFXE2EXBFFEIQH5FM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G3YM2GHJAJFXE2EXBFFEIQH5FM","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":"b3d632ff93ee9f92e2fab962118457b2f8fc85fe658aa97843ae82a225d83e99","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-23T17:54:45Z","title_canon_sha256":"96804992504421cd89b7aa5b88601b1c8a36ef782a36c27c5c84b9eb43362321"},"schema_version":"1.0","source":{"id":"2112.12743","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.12743","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2112.12743v1","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12743","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"G3YM2GHJAJFX","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"G3YM2GHJAJFXE2EX","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"G3YM2GHJ","created_at":"2026-07-05T03:43:30Z"}],"graph_snapshots":[{"event_id":"sha256:7882eed08123e9a5a8894ec46a2e7d038a8d6b7515fe404fa4cc3d8be0d0c305","target":"graph","created_at":"2026-07-05T03:43:30Z","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/2112.12743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the existing cross-speaker style transfer task, a source speaker with multi-style recordings is necessary to provide the style for a target speaker. However, it is hard for one speaker to express all expected styles. In this paper, a more general task, which is to produce expressive speech by combining any styles and timbres from a multi-speaker corpus in which each speaker has a unique style, is proposed. To realize this task, a novel method is proposed. This method is a Tacotron2-based framework but with a fine-grained text-based prosody predicting module and a speaker identity controller","authors_text":"Guanglu Wan, Guoqiao Yu, Lei Xie, Qicong Xie, Tao Li, Xinsheng Wang, Zhichao Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-23T17:54:45Z","title":"Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12743","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:b5abf28a649a7376664f4e85056889a58493f05646ff1dc78f1fe59c2fd7e854","target":"record","created_at":"2026-07-05T03:43:30Z","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":"b3d632ff93ee9f92e2fab962118457b2f8fc85fe658aa97843ae82a225d83e99","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-23T17:54:45Z","title_canon_sha256":"96804992504421cd89b7aa5b88601b1c8a36ef782a36c27c5c84b9eb43362321"},"schema_version":"1.0","source":{"id":"2112.12743","kind":"arxiv","version":1}},"canonical_sha256":"36f0cd18e9024b726897094a4440fd2b30ca78b8cdc5e9fc3a9238f7a28d0f4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36f0cd18e9024b726897094a4440fd2b30ca78b8cdc5e9fc3a9238f7a28d0f4c","first_computed_at":"2026-07-05T03:43:30.812262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:43:30.812262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Femrd33Ne7V2aSSrOtIA3JAgvozXODX3x+1lKDZsLsv9lOv3MgTqMR3wiGsdSBjm+bQUYQ360rWXtbO+UPKqBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:43:30.812705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.12743","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5abf28a649a7376664f4e85056889a58493f05646ff1dc78f1fe59c2fd7e854","sha256:7882eed08123e9a5a8894ec46a2e7d038a8d6b7515fe404fa4cc3d8be0d0c305"],"state_sha256":"48b6a22f4c5898de005f79a1f5803a9a49f308034da893838da91866b542b175"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KwQ4NRQ8zFr+b3li7oHIRnDZ+36JCg3vYA/wdQa+f2nlfREwgZZqJtkfqRG2VF6Ll+pAgNV5n4E/NfPYOuMWCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T10:43:23.207448Z","bundle_sha256":"06970a58d53342905ff86ad93b3c73c3d61c62044be8e669281b6b54db4d949a"}}