{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7KY3PNIAXYKYF5JQOCKRPM373J","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":"63a1341dc76b3712de03376fd71e0ef19e83f3be0f0fa4a64738d4e35ad1d813","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-25T06:46:36Z","title_canon_sha256":"637de7fa8b6a8fd8530ac93c3fcd2c9c986588dc6580ecb8a69c2a8fb5b2c272"},"schema_version":"1.0","source":{"id":"2306.14145","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14145","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14145v1","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14145","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"pith_short_12","alias_value":"7KY3PNIAXYKY","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"pith_short_16","alias_value":"7KY3PNIAXYKYF5JQ","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"pith_short_8","alias_value":"7KY3PNIA","created_at":"2026-07-05T06:24:32Z"}],"graph_snapshots":[{"event_id":"sha256:0f814d4084236112e338ce0a902f09bddcfb09ceebe06335705a6043731974a0","target":"graph","created_at":"2026-07-05T06:24:32Z","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/2306.14145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although high-fidelity speech can be obtained for intralingual speech synthesis, cross-lingual text-to-speech (CTTS) is still far from satisfactory as it is difficult to accurately retain the speaker timbres(i.e. speaker similarity) and eliminate the accents from their first language(i.e. nativeness). In this paper, we demonstrated that vector-quantized(VQ) acoustic feature contains less speaker information than mel-spectrogram. Based on this finding, we propose a novel dual speaker embedding TTS (DSE-TTS) framework for CTTS with authentic speaking style. Here, one embedding is fed to the acou","authors_text":"Chenpeng Du, Kai Yu, Sen Liu, Xie Chen, Yiwei Guo","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-25T06:46:36Z","title":"DSE-TTS: Dual Speaker Embedding for Cross-Lingual Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14145","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":"sha256:4b74498f4fc926ccaf900dc73cd8bfcb6df342db13943778be85a625934e32a7","target":"record","created_at":"2026-07-05T06:24:32Z","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":"63a1341dc76b3712de03376fd71e0ef19e83f3be0f0fa4a64738d4e35ad1d813","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-25T06:46:36Z","title_canon_sha256":"637de7fa8b6a8fd8530ac93c3fcd2c9c986588dc6580ecb8a69c2a8fb5b2c272"},"schema_version":"1.0","source":{"id":"2306.14145","kind":"arxiv","version":1}},"canonical_sha256":"fab1b7b500be1582f530709517b37fda64997cb5b2036b9cb1f00cf2053296c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fab1b7b500be1582f530709517b37fda64997cb5b2036b9cb1f00cf2053296c0","first_computed_at":"2026-07-05T06:24:32.285867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:32.285867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A0wKO0NzxkUlhe2Cq12aD1ZUWI9O73WiH9E/Me0mHNpQx9Rx48P3JwwajvJuUfxYcK7alKzYXN8UX72x8OkdBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:32.286292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14145","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b74498f4fc926ccaf900dc73cd8bfcb6df342db13943778be85a625934e32a7","sha256:0f814d4084236112e338ce0a902f09bddcfb09ceebe06335705a6043731974a0"],"state_sha256":"b7e8b88438108435a51c5afd08095c249b995e64e6cce6b2da310d0a4cbc8977"}