{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BPUBS2R7BGOJB5OWBP42T3FP3Z","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":"14ef9eb69555e3b067c7a3a56dcc74a133f4c4db8370de6e2df4e22616da3390","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-06-25T05:29:48Z","title_canon_sha256":"b7f013a710872cfbd4e961418833df16a4bd9ae50aa6bca317bcc562f50c7ad8"},"schema_version":"1.0","source":{"id":"2206.12559","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12559","created_at":"2026-07-05T04:34:56Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12559v1","created_at":"2026-07-05T04:34:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12559","created_at":"2026-07-05T04:34:56Z"},{"alias_kind":"pith_short_12","alias_value":"BPUBS2R7BGOJ","created_at":"2026-07-05T04:34:56Z"},{"alias_kind":"pith_short_16","alias_value":"BPUBS2R7BGOJB5OW","created_at":"2026-07-05T04:34:56Z"},{"alias_kind":"pith_short_8","alias_value":"BPUBS2R7","created_at":"2026-07-05T04:34:56Z"}],"graph_snapshots":[{"event_id":"sha256:ee0d58a042b04e5c53b01dab9888ebfe181a7435000b74110511cd794e291ba4","target":"graph","created_at":"2026-07-05T04:34:56Z","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/2206.12559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is costly to acquire and difficult to define and annotate accurately. In this paper, we propose a novel framework for learning style representation from abundant plain text in a self-supervised manner. It leverages an emotion lexicon and uses contrastive learning and deep clustering. We further integrate the style representation as a conditioned embedding in a ","authors_text":"Jian-Yun Nie, Lei He, Ruihua Song, Shaofei Zhang, Xi Wang, Yihan Wu","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-06-25T05:29:48Z","title":"Self-supervised Context-aware Style Representation for Expressive Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12559","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":"sha256:0e4fea9b909711e7b7bfc2d60d465aee4dc6d78312b75f47e88dc46a4bfc9308","target":"record","created_at":"2026-07-05T04:34:56Z","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":"14ef9eb69555e3b067c7a3a56dcc74a133f4c4db8370de6e2df4e22616da3390","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-06-25T05:29:48Z","title_canon_sha256":"b7f013a710872cfbd4e961418833df16a4bd9ae50aa6bca317bcc562f50c7ad8"},"schema_version":"1.0","source":{"id":"2206.12559","kind":"arxiv","version":1}},"canonical_sha256":"0be8196a3f099c90f5d60bf9a9ecafde48e2fbbafcf5ca6abb164735f587c268","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0be8196a3f099c90f5d60bf9a9ecafde48e2fbbafcf5ca6abb164735f587c268","first_computed_at":"2026-07-05T04:34:56.440673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:56.440673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NHeUUvBzBmj0UBwSbMw/vMY4f8xRM6qzKS7ack9aNrXn1N3SFB8Y2AJQjuF3etg/MOF9McuZJLay1PKLM/3ZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:56.441142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.12559","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e4fea9b909711e7b7bfc2d60d465aee4dc6d78312b75f47e88dc46a4bfc9308","sha256:ee0d58a042b04e5c53b01dab9888ebfe181a7435000b74110511cd794e291ba4"],"state_sha256":"422375e3f93231629c481886bca9d054f981142a28323667a300cc2ec0834299"}