{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:57GZEN3MEYF4JEIB7QALKP52TT","short_pith_number":"pith:57GZEN3M","canonical_record":{"source":{"id":"2511.01056","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-11-02T19:18:38Z","cross_cats_sorted":[],"title_canon_sha256":"cfbe1529d2a118e40766ac581c7dc29ddd43a6417974fd313d005607c9551a00","abstract_canon_sha256":"2a126408d8ae2258435b6e408fc1d7ad97861ff987caa32483034051fa8acb1c"},"schema_version":"1.0"},"canonical_sha256":"efcd92376c260bc49101fc00b53fba9ce550803a7325f17d6e287cfde04f47ab","source":{"kind":"arxiv","id":"2511.01056","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.01056","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2511.01056v3","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.01056","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"57GZEN3MEYF4","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"57GZEN3MEYF4JEIB","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"57GZEN3M","created_at":"2026-07-21T01:21:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:57GZEN3MEYF4JEIB7QALKP52TT","target":"record","payload":{"canonical_record":{"source":{"id":"2511.01056","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-11-02T19:18:38Z","cross_cats_sorted":[],"title_canon_sha256":"cfbe1529d2a118e40766ac581c7dc29ddd43a6417974fd313d005607c9551a00","abstract_canon_sha256":"2a126408d8ae2258435b6e408fc1d7ad97861ff987caa32483034051fa8acb1c"},"schema_version":"1.0"},"canonical_sha256":"efcd92376c260bc49101fc00b53fba9ce550803a7325f17d6e287cfde04f47ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:40.638093Z","signature_b64":"eOXlgc0mdiiMX6fNPxWxKlrg2VETZaB+TfxcnzroG11+6vFoSEhkFlBHkFCCxs2ttRxyZsIoh5gwJnMgNDNkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efcd92376c260bc49101fc00b53fba9ce550803a7325f17d6e287cfde04f47ab","last_reissued_at":"2026-07-21T01:21:40.637149Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:40.637149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.01056","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-21T01:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"af8eFT9tUz0TuVdCLqc3+b5gfpp1zQO8lhCoF2gwxR0XTn/inipxWKIuOB4vXSUr8yslzyWmtKFS8i4pXcBWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:53:36.520842Z"},"content_sha256":"bc2b17615f28eb34ca658218f2245139b92c4d2ef75cbe1a4bf7960e0cc80747","schema_version":"1.0","event_id":"sha256:bc2b17615f28eb34ca658218f2245139b92c4d2ef75cbe1a4bf7960e0cc80747"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:57GZEN3MEYF4JEIB7QALKP52TT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WhisperVC: Decoupled Cross-Domain Alignment and Speech Generation for Low-Resource Whisper-to-Normal Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dong Liu, Juan Liu, Ming Li, Wei Ju, Yao Tian","submitted_at":"2025-11-02T19:18:38Z","abstract_excerpt":"Whispered speech lacks vocal-fold excitation, making intelligible conversion challenging. We propose WhisperVC, a three-stage framework for low-resource whisper-to-normal (W2N) conversion that decouples cross-domain alignment from speech generation. Stage 1 uses limited paired whisper-normal data with a content encoder and a Conformer-based variational autoencoder (VAE) with soft-DTW alignment to learn domain-invariant semantic representations. Stage 2, trained only on normal speech, employs a Length-Channel Aligner and a two-stage speaker-conditioned mel generator for timbre and prosody model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.01056","kind":"arxiv","version":3},"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/2511.01056/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":"2026-07-21T01:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cRWozcIrnHFgpPUldgxII8yVljvs4AZiMWU/nNj+wVzr6OSAhwNPb+BeuJ/jWFUqZqE42n3OoALHSj0Z9HccCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:53:36.521332Z"},"content_sha256":"f5a442a3fe408aba50684f54aeca38ed20ff3fcecab83319e99ab85c78f213ba","schema_version":"1.0","event_id":"sha256:f5a442a3fe408aba50684f54aeca38ed20ff3fcecab83319e99ab85c78f213ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57GZEN3MEYF4JEIB7QALKP52TT/bundle.json","state_url":"https://pith.science/pith/57GZEN3MEYF4JEIB7QALKP52TT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57GZEN3MEYF4JEIB7QALKP52TT/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":"2026-08-08T23:53:36Z","links":{"resolver":"https://pith.science/pith/57GZEN3MEYF4JEIB7QALKP52TT","bundle":"https://pith.science/pith/57GZEN3MEYF4JEIB7QALKP52TT/bundle.json","state":"https://pith.science/pith/57GZEN3MEYF4JEIB7QALKP52TT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57GZEN3MEYF4JEIB7QALKP52TT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:57GZEN3MEYF4JEIB7QALKP52TT","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":"2a126408d8ae2258435b6e408fc1d7ad97861ff987caa32483034051fa8acb1c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-11-02T19:18:38Z","title_canon_sha256":"cfbe1529d2a118e40766ac581c7dc29ddd43a6417974fd313d005607c9551a00"},"schema_version":"1.0","source":{"id":"2511.01056","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.01056","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2511.01056v3","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.01056","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"57GZEN3MEYF4","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"57GZEN3MEYF4JEIB","created_at":"2026-07-21T01:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"57GZEN3M","created_at":"2026-07-21T01:21:40Z"}],"graph_snapshots":[{"event_id":"sha256:f5a442a3fe408aba50684f54aeca38ed20ff3fcecab83319e99ab85c78f213ba","target":"graph","created_at":"2026-07-21T01:21:40Z","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/2511.01056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Whispered speech lacks vocal-fold excitation, making intelligible conversion challenging. We propose WhisperVC, a three-stage framework for low-resource whisper-to-normal (W2N) conversion that decouples cross-domain alignment from speech generation. Stage 1 uses limited paired whisper-normal data with a content encoder and a Conformer-based variational autoencoder (VAE) with soft-DTW alignment to learn domain-invariant semantic representations. Stage 2, trained only on normal speech, employs a Length-Channel Aligner and a two-stage speaker-conditioned mel generator for timbre and prosody model","authors_text":"Dong Liu, Juan Liu, Ming Li, Wei Ju, Yao Tian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-11-02T19:18:38Z","title":"WhisperVC: Decoupled Cross-Domain Alignment and Speech Generation for Low-Resource Whisper-to-Normal Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.01056","kind":"arxiv","version":3},"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:bc2b17615f28eb34ca658218f2245139b92c4d2ef75cbe1a4bf7960e0cc80747","target":"record","created_at":"2026-07-21T01:21:40Z","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":"2a126408d8ae2258435b6e408fc1d7ad97861ff987caa32483034051fa8acb1c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-11-02T19:18:38Z","title_canon_sha256":"cfbe1529d2a118e40766ac581c7dc29ddd43a6417974fd313d005607c9551a00"},"schema_version":"1.0","source":{"id":"2511.01056","kind":"arxiv","version":3}},"canonical_sha256":"efcd92376c260bc49101fc00b53fba9ce550803a7325f17d6e287cfde04f47ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efcd92376c260bc49101fc00b53fba9ce550803a7325f17d6e287cfde04f47ab","first_computed_at":"2026-07-21T01:21:40.637149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:40.637149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eOXlgc0mdiiMX6fNPxWxKlrg2VETZaB+TfxcnzroG11+6vFoSEhkFlBHkFCCxs2ttRxyZsIoh5gwJnMgNDNkAw==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:40.638093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.01056","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc2b17615f28eb34ca658218f2245139b92c4d2ef75cbe1a4bf7960e0cc80747","sha256:f5a442a3fe408aba50684f54aeca38ed20ff3fcecab83319e99ab85c78f213ba"],"state_sha256":"1f1981c32d6eabda48b4bf66038623f1adf9a16731db6219dbc378f0a92e0966"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0tdU3wWgnItaFm++buMx3PpziDdqHYwGCIvrnywletqf89W7QPxQstMVaJzG6bMEdr0lpbe45XaxHMXfpt4JAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:53:36.524933Z","bundle_sha256":"d5f20c808a00212cb13a1d455ea4c9d8b83a0d43e0d496bcb1f8985fab52a4fa"}}