{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DSG372VHW6SBOIKP3X6UXV34CF","short_pith_number":"pith:DSG372VH","canonical_record":{"source":{"id":"2110.03887","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-08T04:19:19Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8833707019a0a4f1a93933534800802684639b9ac54fef950fc36cccf68381e5","abstract_canon_sha256":"5901b5c45d694f6a9859fd3ff6034d8528ea4cc2b26e2c052f579ef79b28a3e0"},"schema_version":"1.0"},"canonical_sha256":"1c8dbfeaa7b7a417214fddfd4bd77c11408b5154e5f71228cfdbeb67b930f42c","source":{"kind":"arxiv","id":"2110.03887","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03887","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03887v4","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03887","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"DSG372VHW6SB","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"DSG372VHW6SBOIKP","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"DSG372VH","created_at":"2026-07-05T04:46:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DSG372VHW6SBOIKP3X6UXV34CF","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03887","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-08T04:19:19Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8833707019a0a4f1a93933534800802684639b9ac54fef950fc36cccf68381e5","abstract_canon_sha256":"5901b5c45d694f6a9859fd3ff6034d8528ea4cc2b26e2c052f579ef79b28a3e0"},"schema_version":"1.0"},"canonical_sha256":"1c8dbfeaa7b7a417214fddfd4bd77c11408b5154e5f71228cfdbeb67b930f42c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:33.060935Z","signature_b64":"bXjtkagbx1eTACxJ2XJUzg6huwTGWJx0zqi95iHLnolkrViyLJUI2IsapZH8PZESDRefVj/evaWceTc1MWuSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c8dbfeaa7b7a417214fddfd4bd77c11408b5154e5f71228cfdbeb67b930f42c","last_reissued_at":"2026-07-05T04:46:33.060353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:33.060353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03887","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gvO3OY+l5NleWMygJ0DhhGKngZMg5uRYZZuZV3ys6IVzXpovIUuy/BFeGDPfeklBMCZJ6Tdta++yuvYgOWzxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:52:40.035291Z"},"content_sha256":"49ed1ad3b6af99d3ac569db99e1005294d809fe8d28e36d117eea1799d381de7","schema_version":"1.0","event_id":"sha256:49ed1ad3b6af99d3ac569db99e1005294d809fe8d28e36d117eea1799d381de7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DSG372VHW6SBOIKP3X6UXV34CF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Environment Aware Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daxin Tan, Guangyan Zhang, Tan Lee","submitted_at":"2021-10-08T04:19:19Z","abstract_excerpt":"This study aims at designing an environment-aware text-to-speech (TTS) system that can generate speech to suit specific acoustic environments. It is also motivated by the desire to leverage massive data of speech audio from heterogeneous sources in TTS system development. The key idea is to model the acoustic environment in speech audio as a factor of data variability and incorporate it as a condition in the process of neural network based speech synthesis. Two embedding extractors are trained with two purposely constructed datasets for characterization and disentanglement of speaker and envir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03887","kind":"arxiv","version":4},"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/2110.03887/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":"2026-07-05T04:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yjfjn05+sgcROzdJm4TL/bAytmn8ZBkoFabA+aj7bnTcRWeLnowqNN+oq9yCLE/EMCNbdZekWV0Z5miaGVsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:52:40.035786Z"},"content_sha256":"c626c492f74266af0f2aa037d185889b5c72cf3f9c3578813309f1caa68ee7dc","schema_version":"1.0","event_id":"sha256:c626c492f74266af0f2aa037d185889b5c72cf3f9c3578813309f1caa68ee7dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSG372VHW6SBOIKP3X6UXV34CF/bundle.json","state_url":"https://pith.science/pith/DSG372VHW6SBOIKP3X6UXV34CF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSG372VHW6SBOIKP3X6UXV34CF/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":"2026-08-08T12:52:40Z","links":{"resolver":"https://pith.science/pith/DSG372VHW6SBOIKP3X6UXV34CF","bundle":"https://pith.science/pith/DSG372VHW6SBOIKP3X6UXV34CF/bundle.json","state":"https://pith.science/pith/DSG372VHW6SBOIKP3X6UXV34CF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSG372VHW6SBOIKP3X6UXV34CF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DSG372VHW6SBOIKP3X6UXV34CF","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":"5901b5c45d694f6a9859fd3ff6034d8528ea4cc2b26e2c052f579ef79b28a3e0","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-08T04:19:19Z","title_canon_sha256":"8833707019a0a4f1a93933534800802684639b9ac54fef950fc36cccf68381e5"},"schema_version":"1.0","source":{"id":"2110.03887","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03887","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03887v4","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03887","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"DSG372VHW6SB","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"DSG372VHW6SBOIKP","created_at":"2026-07-05T04:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"DSG372VH","created_at":"2026-07-05T04:46:33Z"}],"graph_snapshots":[{"event_id":"sha256:c626c492f74266af0f2aa037d185889b5c72cf3f9c3578813309f1caa68ee7dc","target":"graph","created_at":"2026-07-05T04:46:33Z","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/2110.03887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study aims at designing an environment-aware text-to-speech (TTS) system that can generate speech to suit specific acoustic environments. It is also motivated by the desire to leverage massive data of speech audio from heterogeneous sources in TTS system development. The key idea is to model the acoustic environment in speech audio as a factor of data variability and incorporate it as a condition in the process of neural network based speech synthesis. Two embedding extractors are trained with two purposely constructed datasets for characterization and disentanglement of speaker and envir","authors_text":"Daxin Tan, Guangyan Zhang, Tan Lee","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-08T04:19:19Z","title":"Environment Aware Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03887","kind":"arxiv","version":4},"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":"sha256:49ed1ad3b6af99d3ac569db99e1005294d809fe8d28e36d117eea1799d381de7","target":"record","created_at":"2026-07-05T04:46:33Z","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":"5901b5c45d694f6a9859fd3ff6034d8528ea4cc2b26e2c052f579ef79b28a3e0","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-08T04:19:19Z","title_canon_sha256":"8833707019a0a4f1a93933534800802684639b9ac54fef950fc36cccf68381e5"},"schema_version":"1.0","source":{"id":"2110.03887","kind":"arxiv","version":4}},"canonical_sha256":"1c8dbfeaa7b7a417214fddfd4bd77c11408b5154e5f71228cfdbeb67b930f42c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c8dbfeaa7b7a417214fddfd4bd77c11408b5154e5f71228cfdbeb67b930f42c","first_computed_at":"2026-07-05T04:46:33.060353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:33.060353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bXjtkagbx1eTACxJ2XJUzg6huwTGWJx0zqi95iHLnolkrViyLJUI2IsapZH8PZESDRefVj/evaWceTc1MWuSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:33.060935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03887","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49ed1ad3b6af99d3ac569db99e1005294d809fe8d28e36d117eea1799d381de7","sha256:c626c492f74266af0f2aa037d185889b5c72cf3f9c3578813309f1caa68ee7dc"],"state_sha256":"97b9b8c16677f066c426c84fbe388714c37c005befa49bac3dea86a0f6948a67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PoHX05mDMv6Cy6mr3jHK5abv7Hp7rErMO7phS1ADh+SsqyyXgUqByKuXU/nmts1MFUmu2to369h/13txNUm/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:52:40.041538Z","bundle_sha256":"4141d9d91188071a3a1bb19343fe182a85db0af0abed938e89921b7d1d593939"}}