{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NM5XDEIXJSVOTDPE6IAE35A2TX","short_pith_number":"pith:NM5XDEIX","canonical_record":{"source":{"id":"2310.17101","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-26T01:58:38Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a9d534a88f79965339a1a18b52e72febe7788c0bcdfe668900412825b92c47a5","abstract_canon_sha256":"c9a655a3bff8d8ab56d362c4120edfcf240a23a952927c77ffd679051d60f205"},"schema_version":"1.0"},"canonical_sha256":"6b3b7191174caae98de4f2004df41a9def5210e9e6b5d276ab31c3266d27dd48","source":{"kind":"arxiv","id":"2310.17101","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17101","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17101v2","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17101","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"pith_short_12","alias_value":"NM5XDEIXJSVO","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"pith_short_16","alias_value":"NM5XDEIXJSVOTDPE","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"pith_short_8","alias_value":"NM5XDEIX","created_at":"2026-07-05T08:11:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NM5XDEIXJSVOTDPE6IAE35A2TX","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17101","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-26T01:58:38Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a9d534a88f79965339a1a18b52e72febe7788c0bcdfe668900412825b92c47a5","abstract_canon_sha256":"c9a655a3bff8d8ab56d362c4120edfcf240a23a952927c77ffd679051d60f205"},"schema_version":"1.0"},"canonical_sha256":"6b3b7191174caae98de4f2004df41a9def5210e9e6b5d276ab31c3266d27dd48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:55.058948Z","signature_b64":"cWqnn7hCr39ayhQk+mrOUkzybXAcExlzBc88cHgIF803EoL0ojM5Wh8DI9k/ihJxeQ+99fXq7ypb9RGZI0o1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b3b7191174caae98de4f2004df41a9def5210e9e6b5d276ab31c3266d27dd48","last_reissued_at":"2026-07-05T08:11:55.058483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:55.058483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17101","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:11:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6c+Qz/fsfrYUvE7fe43j2Hln9cob1YxM2aQrNHnSrPxXil3bufZZYWSjhjgJaWXXbB4x5U/KhI+6ZSXkW8/+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:05:00.497467Z"},"content_sha256":"731be503f7c74eb65e5229f9ef98f433d481a45d4737688439199c335ac6a672","schema_version":"1.0","event_id":"sha256:731be503f7c74eb65e5229f9ef98f433d481a45d4737688439199c335ac6a672"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NM5XDEIXJSVOTDPE6IAE35A2TX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Multi-Speaker Expressive Speech Synthesis with Semi-supervised Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Guoqing Zhao, Lei Xie, Ning Jiang, Xinfa Zhu, Yi Lei, Yuke Li","submitted_at":"2023-10-26T01:58:38Z","abstract_excerpt":"This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfer style and emotion across speakers. Specifically, contrastive learning from different levels, i.e. utterance and category level, is leveraged to extract the disentangled style, emotion, and speaker representations from speech for style and emotion transfer. Furthermore, a semi-supervised training strategy is introduced to improve the data utilization efficiency by involving mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17101","kind":"arxiv","version":2},"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/2310.17101/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":"2026-07-05T08:11:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTXMLTFr7yeyM2zQArftsCqxYfwggmv6hhMtJHmKFXmQYY9mlaJmIjsvxGM6HAjC0DLre4ZB6sFhpv/e98fmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:05:00.498842Z"},"content_sha256":"1a7824998423f675c0adb4b1915eb5001145cfc02abac2a555fdc986613d8694","schema_version":"1.0","event_id":"sha256:1a7824998423f675c0adb4b1915eb5001145cfc02abac2a555fdc986613d8694"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NM5XDEIXJSVOTDPE6IAE35A2TX/bundle.json","state_url":"https://pith.science/pith/NM5XDEIXJSVOTDPE6IAE35A2TX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NM5XDEIXJSVOTDPE6IAE35A2TX/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":"2026-08-13T02:05:00Z","links":{"resolver":"https://pith.science/pith/NM5XDEIXJSVOTDPE6IAE35A2TX","bundle":"https://pith.science/pith/NM5XDEIXJSVOTDPE6IAE35A2TX/bundle.json","state":"https://pith.science/pith/NM5XDEIXJSVOTDPE6IAE35A2TX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NM5XDEIXJSVOTDPE6IAE35A2TX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NM5XDEIXJSVOTDPE6IAE35A2TX","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":"c9a655a3bff8d8ab56d362c4120edfcf240a23a952927c77ffd679051d60f205","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-26T01:58:38Z","title_canon_sha256":"a9d534a88f79965339a1a18b52e72febe7788c0bcdfe668900412825b92c47a5"},"schema_version":"1.0","source":{"id":"2310.17101","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17101","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17101v2","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17101","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"pith_short_12","alias_value":"NM5XDEIXJSVO","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"pith_short_16","alias_value":"NM5XDEIXJSVOTDPE","created_at":"2026-07-05T08:11:55Z"},{"alias_kind":"pith_short_8","alias_value":"NM5XDEIX","created_at":"2026-07-05T08:11:55Z"}],"graph_snapshots":[{"event_id":"sha256:1a7824998423f675c0adb4b1915eb5001145cfc02abac2a555fdc986613d8694","target":"graph","created_at":"2026-07-05T08:11:55Z","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/2310.17101/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfer style and emotion across speakers. Specifically, contrastive learning from different levels, i.e. utterance and category level, is leveraged to extract the disentangled style, emotion, and speaker representations from speech for style and emotion transfer. Furthermore, a semi-supervised training strategy is introduced to improve the data utilization efficiency by involving mu","authors_text":"Guoqing Zhao, Lei Xie, Ning Jiang, Xinfa Zhu, Yi Lei, Yuke Li","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-26T01:58:38Z","title":"Boosting Multi-Speaker Expressive Speech Synthesis with Semi-supervised Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17101","kind":"arxiv","version":2},"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":"sha256:731be503f7c74eb65e5229f9ef98f433d481a45d4737688439199c335ac6a672","target":"record","created_at":"2026-07-05T08:11:55Z","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":"c9a655a3bff8d8ab56d362c4120edfcf240a23a952927c77ffd679051d60f205","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-26T01:58:38Z","title_canon_sha256":"a9d534a88f79965339a1a18b52e72febe7788c0bcdfe668900412825b92c47a5"},"schema_version":"1.0","source":{"id":"2310.17101","kind":"arxiv","version":2}},"canonical_sha256":"6b3b7191174caae98de4f2004df41a9def5210e9e6b5d276ab31c3266d27dd48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b3b7191174caae98de4f2004df41a9def5210e9e6b5d276ab31c3266d27dd48","first_computed_at":"2026-07-05T08:11:55.058483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:55.058483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cWqnn7hCr39ayhQk+mrOUkzybXAcExlzBc88cHgIF803EoL0ojM5Wh8DI9k/ihJxeQ+99fXq7ypb9RGZI0o1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:55.058948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17101","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:731be503f7c74eb65e5229f9ef98f433d481a45d4737688439199c335ac6a672","sha256:1a7824998423f675c0adb4b1915eb5001145cfc02abac2a555fdc986613d8694"],"state_sha256":"578b7aacce00a05df5fec3f7404c581a2980edb972d5053022183619b42d12eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hHhab2LsK0no4dtyDKIL4ftYale+4pWarQvwFbi8ZaasfHQjX+pGP6waChXaaEqN7AfINOgC3G8wShs5KYdqDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T02:05:00.504935Z","bundle_sha256":"8a556221e8fc23a44faae1363af135b672e0c036e487ed4fb167046652d535d0"}}