{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DUPVHTOULYNQW2JWS2THP4OBIG","short_pith_number":"pith:DUPVHTOU","canonical_record":{"source":{"id":"2406.03637","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T22:17:47Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"db0d049193074588275d58b54d8bb5189a467a3b33904a9e663fd97c53f9a43d","abstract_canon_sha256":"011f1d50f503397b0b7324ee339986abdb35192b2b72fbc6d988810c0dab24a9"},"schema_version":"1.0"},"canonical_sha256":"1d1f53cdd45e1b0b693696a677f1c14189285f7324eb31c6aa70a40cbd1ce26c","source":{"kind":"arxiv","id":"2406.03637","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03637","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03637v2","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03637","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"pith_short_12","alias_value":"DUPVHTOULYNQ","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"pith_short_16","alias_value":"DUPVHTOULYNQW2JW","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"pith_short_8","alias_value":"DUPVHTOU","created_at":"2026-07-05T09:27:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DUPVHTOULYNQW2JWS2THP4OBIG","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03637","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T22:17:47Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"db0d049193074588275d58b54d8bb5189a467a3b33904a9e663fd97c53f9a43d","abstract_canon_sha256":"011f1d50f503397b0b7324ee339986abdb35192b2b72fbc6d988810c0dab24a9"},"schema_version":"1.0"},"canonical_sha256":"1d1f53cdd45e1b0b693696a677f1c14189285f7324eb31c6aa70a40cbd1ce26c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:01.792526Z","signature_b64":"m2igiLk51D49ILkBkQ0wHi8lZ0gV2B5gemCfcOTEJq+BxXIystT4b2VuAqwK32Isfy957oa+vm22u7JF9+/dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d1f53cdd45e1b0b693696a677f1c14189285f7324eb31c6aa70a40cbd1ce26c","last_reissued_at":"2026-07-05T09:27:01.792060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:01.792060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03637","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":"2026-07-05T09:27:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ND6U/ZKDohFRtlfGBiExuHOVOd8GN3X9+XNT8Nsk6fSSlg0BBpqQZglz2qNRJ0gAR/sDviidOzHzYwue6HsoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:18:44.861032Z"},"content_sha256":"6cf0642b89039fc06e04ba4088ad4eef08c5da44efcc18ea41d6bb322aca0b34","schema_version":"1.0","event_id":"sha256:6cf0642b89039fc06e04ba4088ad4eef08c5da44efcc18ea41d6bb322aca0b34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DUPVHTOULYNQW2JWS2THP4OBIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Style Mixture of Experts for Expressive Text-To-Speech Synthesis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahad Jawaid, Berrak Sisman, Junchen Lu, Shreeram Suresh Chandra","submitted_at":"2024-06-05T22:17:47Z","abstract_excerpt":"Recent advances in style transfer text-to-speech (TTS) have improved the expressiveness of synthesized speech. However, encoding stylistic information (e.g., timbre, emotion, and prosody) from diverse and unseen reference speech remains a challenge. This paper introduces StyleMoE, an approach that addresses the issue of learning averaged style representations in the style encoder by creating style experts that learn from subsets of data. The proposed method replaces the style encoder in a TTS framework with a Mixture of Experts (MoE) layer. The style experts specialize by learning from subsets"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03637","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/2406.03637/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":"2026-07-05T09:27:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IjihU8Q/2IXFP7YLCRGSa8wMem1oTlT3rzsetKCLfb0nvhdbxieAX7LvI0b1L4BNgJ1o4/ecV+Mc7K+VoB9ECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:18:44.861868Z"},"content_sha256":"7803bb730df397dd48aa71b697fe60558bae3df63989ca2c014682b15f9ce790","schema_version":"1.0","event_id":"sha256:7803bb730df397dd48aa71b697fe60558bae3df63989ca2c014682b15f9ce790"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DUPVHTOULYNQW2JWS2THP4OBIG/bundle.json","state_url":"https://pith.science/pith/DUPVHTOULYNQW2JWS2THP4OBIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DUPVHTOULYNQW2JWS2THP4OBIG/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":"2026-08-10T16:18:44Z","links":{"resolver":"https://pith.science/pith/DUPVHTOULYNQW2JWS2THP4OBIG","bundle":"https://pith.science/pith/DUPVHTOULYNQW2JWS2THP4OBIG/bundle.json","state":"https://pith.science/pith/DUPVHTOULYNQW2JWS2THP4OBIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DUPVHTOULYNQW2JWS2THP4OBIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DUPVHTOULYNQW2JWS2THP4OBIG","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":"011f1d50f503397b0b7324ee339986abdb35192b2b72fbc6d988810c0dab24a9","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T22:17:47Z","title_canon_sha256":"db0d049193074588275d58b54d8bb5189a467a3b33904a9e663fd97c53f9a43d"},"schema_version":"1.0","source":{"id":"2406.03637","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03637","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03637v2","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03637","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"pith_short_12","alias_value":"DUPVHTOULYNQ","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"pith_short_16","alias_value":"DUPVHTOULYNQW2JW","created_at":"2026-07-05T09:27:01Z"},{"alias_kind":"pith_short_8","alias_value":"DUPVHTOU","created_at":"2026-07-05T09:27:01Z"}],"graph_snapshots":[{"event_id":"sha256:7803bb730df397dd48aa71b697fe60558bae3df63989ca2c014682b15f9ce790","target":"graph","created_at":"2026-07-05T09:27:01Z","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/2406.03637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in style transfer text-to-speech (TTS) have improved the expressiveness of synthesized speech. However, encoding stylistic information (e.g., timbre, emotion, and prosody) from diverse and unseen reference speech remains a challenge. This paper introduces StyleMoE, an approach that addresses the issue of learning averaged style representations in the style encoder by creating style experts that learn from subsets of data. The proposed method replaces the style encoder in a TTS framework with a Mixture of Experts (MoE) layer. The style experts specialize by learning from subsets","authors_text":"Ahad Jawaid, Berrak Sisman, Junchen Lu, Shreeram Suresh Chandra","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T22:17:47Z","title":"Style Mixture of Experts for Expressive Text-To-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03637","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":"sha256:6cf0642b89039fc06e04ba4088ad4eef08c5da44efcc18ea41d6bb322aca0b34","target":"record","created_at":"2026-07-05T09:27:01Z","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":"011f1d50f503397b0b7324ee339986abdb35192b2b72fbc6d988810c0dab24a9","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T22:17:47Z","title_canon_sha256":"db0d049193074588275d58b54d8bb5189a467a3b33904a9e663fd97c53f9a43d"},"schema_version":"1.0","source":{"id":"2406.03637","kind":"arxiv","version":2}},"canonical_sha256":"1d1f53cdd45e1b0b693696a677f1c14189285f7324eb31c6aa70a40cbd1ce26c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d1f53cdd45e1b0b693696a677f1c14189285f7324eb31c6aa70a40cbd1ce26c","first_computed_at":"2026-07-05T09:27:01.792060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:01.792060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m2igiLk51D49ILkBkQ0wHi8lZ0gV2B5gemCfcOTEJq+BxXIystT4b2VuAqwK32Isfy957oa+vm22u7JF9+/dAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:01.792526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03637","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cf0642b89039fc06e04ba4088ad4eef08c5da44efcc18ea41d6bb322aca0b34","sha256:7803bb730df397dd48aa71b697fe60558bae3df63989ca2c014682b15f9ce790"],"state_sha256":"f6f09dfa352d5372e9361e71e58919d45b05bbd2ae34a600bae6f1955193209e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3G/QKJKuA6Ztu7Va5nEos2ZsWWoVClwjiyV1GRZF18Ql4x3D+8B518PWfxuq9TOnQg9Aem6vsYKSd4/BZ/eBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:18:44.867327Z","bundle_sha256":"8c1822884aa023a9d47226ab92926831c77df0a286f52c335949eba5d9d25235"}}