{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FWLFFN5AWKQ3Q6HZICJSKZZRRI","short_pith_number":"pith:FWLFFN5A","canonical_record":{"source":{"id":"2110.07192","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-14T07:37:04Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"5719c299fc265d903fb80861bac23a3cf67fc510afb9f6e32975369d58e131be","abstract_canon_sha256":"ac704e158f35508c1e3270da1585e2537e877a462014320c0d9a277ced6abc78"},"schema_version":"1.0"},"canonical_sha256":"2d9652b7a0b2a1b878f940932567318a05b4f03f769e8ac6a288cc693e2bab82","source":{"kind":"arxiv","id":"2110.07192","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07192","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07192v3","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07192","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"pith_short_12","alias_value":"FWLFFN5AWKQ3","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"pith_short_16","alias_value":"FWLFFN5AWKQ3Q6HZ","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"pith_short_8","alias_value":"FWLFFN5A","created_at":"2026-07-05T04:53:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FWLFFN5AWKQ3Q6HZICJSKZZRRI","target":"record","payload":{"canonical_record":{"source":{"id":"2110.07192","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-14T07:37:04Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"5719c299fc265d903fb80861bac23a3cf67fc510afb9f6e32975369d58e131be","abstract_canon_sha256":"ac704e158f35508c1e3270da1585e2537e877a462014320c0d9a277ced6abc78"},"schema_version":"1.0"},"canonical_sha256":"2d9652b7a0b2a1b878f940932567318a05b4f03f769e8ac6a288cc693e2bab82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:25.502836Z","signature_b64":"DuMQ1aQhYvIqKsJZNr5cB0Q40KVmCqqLIrFfeBzAikA6zVr6zpK6lTovBsEFlHEhtUyZLUrOHsur6ud6jI9TAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d9652b7a0b2a1b878f940932567318a05b4f03f769e8ac6a288cc693e2bab82","last_reissued_at":"2026-07-05T04:53:25.502259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:25.502259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.07192","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":"2026-07-05T04:53:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CEvhm2R9SQNfWPKHjSoC8lCuwyVAMIbHSL1qXudpnpSwLCI6YiXWbmx4tVevlFxgrTNCQ5MtLgtBfFt3e1S0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:33:28.392313Z"},"content_sha256":"d193b6ad6eed83b49c9d619ad83591b0df7c21a92ad8810345a49968b0854b85","schema_version":"1.0","event_id":"sha256:d193b6ad6eed83b49c9d619ad83591b0df7c21a92ad8810345a49968b0854b85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FWLFFN5AWKQ3Q6HZICJSKZZRRI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haitong Zhang, Haoyue Zhan, Xinyuan Yu, Yang Zhang, Yue Lin","submitted_at":"2021-10-14T07:37:04Z","abstract_excerpt":"In this paper, we study the disentanglement of speaker and language representations in non-autoregressive cross-lingual TTS models from various aspects. We propose a phoneme length regulator that solves the length mismatch problem between IPA input sequence and monolingual alignment results. Using the phoneme length regulator, we present a FastPitch-based cross-lingual model with IPA symbols as input representations. Our experiments show that language-independent input representations (e.g. IPA symbols), an increasing number of training speakers, and explicit modeling of speech variance inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07192","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/2110.07192/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":"2026-07-05T04:53:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lPe9FKgAkzsCZVUmyO6ZXbEQPwFXgsi32ogfGHPHCYtZg9C4XFL6hHqMSBC+S0mI6JYN8378da7n3K3A6JRIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:33:28.392757Z"},"content_sha256":"386824ba07e845f735f1e49d4e00e7eac64e6eb08acefc5b8ae54738e45b1ec2","schema_version":"1.0","event_id":"sha256:386824ba07e845f735f1e49d4e00e7eac64e6eb08acefc5b8ae54738e45b1ec2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWLFFN5AWKQ3Q6HZICJSKZZRRI/bundle.json","state_url":"https://pith.science/pith/FWLFFN5AWKQ3Q6HZICJSKZZRRI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWLFFN5AWKQ3Q6HZICJSKZZRRI/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":"2026-08-17T03:33:28Z","links":{"resolver":"https://pith.science/pith/FWLFFN5AWKQ3Q6HZICJSKZZRRI","bundle":"https://pith.science/pith/FWLFFN5AWKQ3Q6HZICJSKZZRRI/bundle.json","state":"https://pith.science/pith/FWLFFN5AWKQ3Q6HZICJSKZZRRI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWLFFN5AWKQ3Q6HZICJSKZZRRI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FWLFFN5AWKQ3Q6HZICJSKZZRRI","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":"ac704e158f35508c1e3270da1585e2537e877a462014320c0d9a277ced6abc78","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-14T07:37:04Z","title_canon_sha256":"5719c299fc265d903fb80861bac23a3cf67fc510afb9f6e32975369d58e131be"},"schema_version":"1.0","source":{"id":"2110.07192","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07192","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07192v3","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07192","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"pith_short_12","alias_value":"FWLFFN5AWKQ3","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"pith_short_16","alias_value":"FWLFFN5AWKQ3Q6HZ","created_at":"2026-07-05T04:53:25Z"},{"alias_kind":"pith_short_8","alias_value":"FWLFFN5A","created_at":"2026-07-05T04:53:25Z"}],"graph_snapshots":[{"event_id":"sha256:386824ba07e845f735f1e49d4e00e7eac64e6eb08acefc5b8ae54738e45b1ec2","target":"graph","created_at":"2026-07-05T04:53:25Z","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/2110.07192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study the disentanglement of speaker and language representations in non-autoregressive cross-lingual TTS models from various aspects. We propose a phoneme length regulator that solves the length mismatch problem between IPA input sequence and monolingual alignment results. Using the phoneme length regulator, we present a FastPitch-based cross-lingual model with IPA symbols as input representations. Our experiments show that language-independent input representations (e.g. IPA symbols), an increasing number of training speakers, and explicit modeling of speech variance inform","authors_text":"Haitong Zhang, Haoyue Zhan, Xinyuan Yu, Yang Zhang, Yue Lin","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-14T07:37:04Z","title":"Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07192","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:d193b6ad6eed83b49c9d619ad83591b0df7c21a92ad8810345a49968b0854b85","target":"record","created_at":"2026-07-05T04:53:25Z","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":"ac704e158f35508c1e3270da1585e2537e877a462014320c0d9a277ced6abc78","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-14T07:37:04Z","title_canon_sha256":"5719c299fc265d903fb80861bac23a3cf67fc510afb9f6e32975369d58e131be"},"schema_version":"1.0","source":{"id":"2110.07192","kind":"arxiv","version":3}},"canonical_sha256":"2d9652b7a0b2a1b878f940932567318a05b4f03f769e8ac6a288cc693e2bab82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d9652b7a0b2a1b878f940932567318a05b4f03f769e8ac6a288cc693e2bab82","first_computed_at":"2026-07-05T04:53:25.502259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:53:25.502259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DuMQ1aQhYvIqKsJZNr5cB0Q40KVmCqqLIrFfeBzAikA6zVr6zpK6lTovBsEFlHEhtUyZLUrOHsur6ud6jI9TAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:53:25.502836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07192","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d193b6ad6eed83b49c9d619ad83591b0df7c21a92ad8810345a49968b0854b85","sha256:386824ba07e845f735f1e49d4e00e7eac64e6eb08acefc5b8ae54738e45b1ec2"],"state_sha256":"01dbc066253857a70541bccff976e55527e255b60af682683f195e41ae0ddd1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2og0n/gl2bgQTp5hmcvh0BELGaER0MADxFVw56WM5IU5gd58O9I7Xo4o1WdasTrSab0Hx77BM/IBnzyf4lkBAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T03:33:28.395509Z","bundle_sha256":"5f80fed0c38108dcf87cf2eaf5deb633dbe10ab1b94afe85aac2fceeefcc7a52"}}