{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:A5JYBV6TJEBZCGAXO4W5XYLA5V","short_pith_number":"pith:A5JYBV6T","canonical_record":{"source":{"id":"2103.04088","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-06T10:14:33Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"7e8df401f113ebc831916a57eda4cc4301604f06024e7e25299fdac8b639caec","abstract_canon_sha256":"06c61474e307aabb427e760dc6d37b251294741bc645f60473f74d28b6769301"},"schema_version":"1.0"},"canonical_sha256":"075380d7d34903911817772ddbe160ed77f7ec42a4a25050248a28d44416f715","source":{"kind":"arxiv","id":"2103.04088","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04088","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04088v5","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04088","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"pith_short_12","alias_value":"A5JYBV6TJEBZ","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"pith_short_16","alias_value":"A5JYBV6TJEBZCGAX","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"pith_short_8","alias_value":"A5JYBV6T","created_at":"2026-07-05T02:36:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:A5JYBV6TJEBZCGAXO4W5XYLA5V","target":"record","payload":{"canonical_record":{"source":{"id":"2103.04088","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-06T10:14:33Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"7e8df401f113ebc831916a57eda4cc4301604f06024e7e25299fdac8b639caec","abstract_canon_sha256":"06c61474e307aabb427e760dc6d37b251294741bc645f60473f74d28b6769301"},"schema_version":"1.0"},"canonical_sha256":"075380d7d34903911817772ddbe160ed77f7ec42a4a25050248a28d44416f715","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:32.533867Z","signature_b64":"IS3MwfkGA2KZBcv5w78J3eIrzWlyy63kFzH0KuqtIxLqZ8TKL+KFYC9vjA1P2O9ax5V6wAjrZLIrF51y9olQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"075380d7d34903911817772ddbe160ed77f7ec42a4a25050248a28d44416f715","last_reissued_at":"2026-07-05T02:36:32.533262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:32.533262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.04088","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:36:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L3tzO1eNoCk++nhhk5iT67MwWR7x1XgaWp9egdl+1ZDfa3RaZ2PbSQUEf+oYWs3U7XjGeK8R8ttRWgPpXIhgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:51:14.431955Z"},"content_sha256":"bfc9de087f7261ce50fe6d5c11d08db18b36c0ef686239e685c22557cff3f7a8","schema_version":"1.0","event_id":"sha256:bfc9de087f7261ce50fe6d5c11d08db18b36c0ef686239e685c22557cff3f7a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:A5JYBV6TJEBZCGAXO4W5XYLA5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chien-yu Huang, Chung-Ming Chien, Hung-yi Lee, Jheng-Hao Lin, Po-chun Hsu","submitted_at":"2021-03-06T10:14:33Z","abstract_excerpt":"The few-shot multi-speaker multi-style voice cloning task is to synthesize utterances with voice and speaking style similar to a reference speaker given only a few reference samples. In this work, we investigate different speaker representations and proposed to integrate pretrained and learnable speaker representations. Among different types of embeddings, the embedding pretrained by voice conversion achieves the best performance. The FastSpeech 2 model combined with both pretrained and learnable speaker representations shows great generalization ability on few-shot speakers and achieved 2nd p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04088","kind":"arxiv","version":5},"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/2103.04088/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":"2026-07-05T02:36:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"70ejmoBTbCVQ1bvZLQnFaA6wqpx5zbUEdGmHiBpAwIsgY9nLlPz9Y1C9F5f6Bm9xdrS3TdlAjyCWH7ksZYSCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:51:14.432298Z"},"content_sha256":"02a65fcd858aec59729c899b1f0e60b4824a06d94fc65574bfc025fdc9b94a44","schema_version":"1.0","event_id":"sha256:02a65fcd858aec59729c899b1f0e60b4824a06d94fc65574bfc025fdc9b94a44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5JYBV6TJEBZCGAXO4W5XYLA5V/bundle.json","state_url":"https://pith.science/pith/A5JYBV6TJEBZCGAXO4W5XYLA5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5JYBV6TJEBZCGAXO4W5XYLA5V/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":"2026-08-06T17:51:14Z","links":{"resolver":"https://pith.science/pith/A5JYBV6TJEBZCGAXO4W5XYLA5V","bundle":"https://pith.science/pith/A5JYBV6TJEBZCGAXO4W5XYLA5V/bundle.json","state":"https://pith.science/pith/A5JYBV6TJEBZCGAXO4W5XYLA5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5JYBV6TJEBZCGAXO4W5XYLA5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:A5JYBV6TJEBZCGAXO4W5XYLA5V","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":"06c61474e307aabb427e760dc6d37b251294741bc645f60473f74d28b6769301","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-06T10:14:33Z","title_canon_sha256":"7e8df401f113ebc831916a57eda4cc4301604f06024e7e25299fdac8b639caec"},"schema_version":"1.0","source":{"id":"2103.04088","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04088","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04088v5","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04088","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"pith_short_12","alias_value":"A5JYBV6TJEBZ","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"pith_short_16","alias_value":"A5JYBV6TJEBZCGAX","created_at":"2026-07-05T02:36:32Z"},{"alias_kind":"pith_short_8","alias_value":"A5JYBV6T","created_at":"2026-07-05T02:36:32Z"}],"graph_snapshots":[{"event_id":"sha256:02a65fcd858aec59729c899b1f0e60b4824a06d94fc65574bfc025fdc9b94a44","target":"graph","created_at":"2026-07-05T02:36:32Z","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/2103.04088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The few-shot multi-speaker multi-style voice cloning task is to synthesize utterances with voice and speaking style similar to a reference speaker given only a few reference samples. In this work, we investigate different speaker representations and proposed to integrate pretrained and learnable speaker representations. Among different types of embeddings, the embedding pretrained by voice conversion achieves the best performance. The FastSpeech 2 model combined with both pretrained and learnable speaker representations shows great generalization ability on few-shot speakers and achieved 2nd p","authors_text":"Chien-yu Huang, Chung-Ming Chien, Hung-yi Lee, Jheng-Hao Lin, Po-chun Hsu","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-06T10:14:33Z","title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04088","kind":"arxiv","version":5},"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:bfc9de087f7261ce50fe6d5c11d08db18b36c0ef686239e685c22557cff3f7a8","target":"record","created_at":"2026-07-05T02:36:32Z","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":"06c61474e307aabb427e760dc6d37b251294741bc645f60473f74d28b6769301","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-06T10:14:33Z","title_canon_sha256":"7e8df401f113ebc831916a57eda4cc4301604f06024e7e25299fdac8b639caec"},"schema_version":"1.0","source":{"id":"2103.04088","kind":"arxiv","version":5}},"canonical_sha256":"075380d7d34903911817772ddbe160ed77f7ec42a4a25050248a28d44416f715","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"075380d7d34903911817772ddbe160ed77f7ec42a4a25050248a28d44416f715","first_computed_at":"2026-07-05T02:36:32.533262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:36:32.533262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IS3MwfkGA2KZBcv5w78J3eIrzWlyy63kFzH0KuqtIxLqZ8TKL+KFYC9vjA1P2O9ax5V6wAjrZLIrF51y9olQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:36:32.533867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.04088","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfc9de087f7261ce50fe6d5c11d08db18b36c0ef686239e685c22557cff3f7a8","sha256:02a65fcd858aec59729c899b1f0e60b4824a06d94fc65574bfc025fdc9b94a44"],"state_sha256":"f2186e7591878b98120b4ae0e77e108d67301dd97d7eb229807550812c2a77f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q3oQO3n73DrFneCHKoaLjWGjIahYmXoCnwauxpAGjPBLvwMnCEFwCqZhYE+6Sbktc4ymll2kYcfjHNrE9fWuBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:51:14.435637Z","bundle_sha256":"6dd8e14eec3a45de3155f2776595951b35cdc2fd4b58949a6fb2a39aaaae62fa"}}