{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CNHR6SDHWPMZCNO5PFSZ6BNU4J","short_pith_number":"pith:CNHR6SDH","canonical_record":{"source":{"id":"2210.15131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-27T02:32:00Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"77b376125f5aaa4d071c0f9d8f8151468d21e0376701e65e2a2f1e78734b2f70","abstract_canon_sha256":"1479ed75fce5df9350192ff0570d598977fd6aa75392cc8c90cb81ce8b25f3de"},"schema_version":"1.0"},"canonical_sha256":"134f1f4867b3d99135dd79659f05b4e2739e6863d1e2fee1bb599e62eca8acfe","source":{"kind":"arxiv","id":"2210.15131","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15131","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15131v1","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15131","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"pith_short_12","alias_value":"CNHR6SDHWPMZ","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"pith_short_16","alias_value":"CNHR6SDHWPMZCNO5","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"pith_short_8","alias_value":"CNHR6SDH","created_at":"2026-07-05T05:11:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CNHR6SDHWPMZCNO5PFSZ6BNU4J","target":"record","payload":{"canonical_record":{"source":{"id":"2210.15131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-27T02:32:00Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"77b376125f5aaa4d071c0f9d8f8151468d21e0376701e65e2a2f1e78734b2f70","abstract_canon_sha256":"1479ed75fce5df9350192ff0570d598977fd6aa75392cc8c90cb81ce8b25f3de"},"schema_version":"1.0"},"canonical_sha256":"134f1f4867b3d99135dd79659f05b4e2739e6863d1e2fee1bb599e62eca8acfe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:02.478403Z","signature_b64":"PiVJ9lhHk415e6gqlyX6rxj8fk7mObxxaIcI3VSAb6yY6iDmPl3MFu793I+qVXsZVgYquWNDi2tpVL+BkTcPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"134f1f4867b3d99135dd79659f05b4e2739e6863d1e2fee1bb599e62eca8acfe","last_reissued_at":"2026-07-05T05:11:02.478043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:02.478043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.15131","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:11:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3DQgIvs8gkfVCD+vKa+zMU1UXfe1R6TmAzcIUj/wMB367IBn3mAP/6GzXpPFLh1otdnGf2wHX3kIRSBoZ7pbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:06:53.430099Z"},"content_sha256":"7208c6ff7b4bc1a328356ce030da415b10104c0ce4307c1c73e7d228da30c428","schema_version":"1.0","event_id":"sha256:7208c6ff7b4bc1a328356ce030da415b10104c0ce4307c1c73e7d228da30c428"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CNHR6SDHWPMZCNO5PFSZ6BNU4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards High-Quality Neural TTS for Low-Resource Languages by Learning Compact Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fenglong Xie, Haohan Guo, Helen Meng, Hui Lu, Xixin Wu","submitted_at":"2022-10-27T02:32:00Z","abstract_excerpt":"This paper aims to enhance low-resource TTS by reducing training data requirements using compact speech representations. A Multi-Stage Multi-Codebook (MSMC) VQ-GAN is trained to learn the representation, MSMCR, and decode it to waveforms. Subsequently, we train the multi-stage predictor to predict MSMCRs from the text for TTS synthesis. Moreover, we optimize the training strategy by leveraging more audio to learn MSMCRs better for low-resource languages. It selects audio from other languages using speaker similarity metric to augment the training set, and applies transfer learning to improve t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15131","kind":"arxiv","version":1},"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/2210.15131/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":"2026-07-05T05:11:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FQ6hO7sOeqBY8djytxyxVh+rd6SUaVTV9K+le5XvVHqwXgdSiH7GmsVIbCf9IUiTpXiOgSL08NOQSN6dIKGnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:06:53.430674Z"},"content_sha256":"dbcb1396b06148d3d3e9dd9e3a6155f653dc1b4fc76fd8ac5a79a2f23deac114","schema_version":"1.0","event_id":"sha256:dbcb1396b06148d3d3e9dd9e3a6155f653dc1b4fc76fd8ac5a79a2f23deac114"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/bundle.json","state_url":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/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":"2026-08-19T16:06:53Z","links":{"resolver":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J","bundle":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/bundle.json","state":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CNHR6SDHWPMZCNO5PFSZ6BNU4J","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":"1479ed75fce5df9350192ff0570d598977fd6aa75392cc8c90cb81ce8b25f3de","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-27T02:32:00Z","title_canon_sha256":"77b376125f5aaa4d071c0f9d8f8151468d21e0376701e65e2a2f1e78734b2f70"},"schema_version":"1.0","source":{"id":"2210.15131","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15131","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15131v1","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15131","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"pith_short_12","alias_value":"CNHR6SDHWPMZ","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"pith_short_16","alias_value":"CNHR6SDHWPMZCNO5","created_at":"2026-07-05T05:11:02Z"},{"alias_kind":"pith_short_8","alias_value":"CNHR6SDH","created_at":"2026-07-05T05:11:02Z"}],"graph_snapshots":[{"event_id":"sha256:dbcb1396b06148d3d3e9dd9e3a6155f653dc1b4fc76fd8ac5a79a2f23deac114","target":"graph","created_at":"2026-07-05T05:11:02Z","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/2210.15131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper aims to enhance low-resource TTS by reducing training data requirements using compact speech representations. A Multi-Stage Multi-Codebook (MSMC) VQ-GAN is trained to learn the representation, MSMCR, and decode it to waveforms. Subsequently, we train the multi-stage predictor to predict MSMCRs from the text for TTS synthesis. Moreover, we optimize the training strategy by leveraging more audio to learn MSMCRs better for low-resource languages. It selects audio from other languages using speaker similarity metric to augment the training set, and applies transfer learning to improve t","authors_text":"Fenglong Xie, Haohan Guo, Helen Meng, Hui Lu, Xixin Wu","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-27T02:32:00Z","title":"Towards High-Quality Neural TTS for Low-Resource Languages by Learning Compact Speech Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15131","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":"sha256:7208c6ff7b4bc1a328356ce030da415b10104c0ce4307c1c73e7d228da30c428","target":"record","created_at":"2026-07-05T05:11:02Z","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":"1479ed75fce5df9350192ff0570d598977fd6aa75392cc8c90cb81ce8b25f3de","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-27T02:32:00Z","title_canon_sha256":"77b376125f5aaa4d071c0f9d8f8151468d21e0376701e65e2a2f1e78734b2f70"},"schema_version":"1.0","source":{"id":"2210.15131","kind":"arxiv","version":1}},"canonical_sha256":"134f1f4867b3d99135dd79659f05b4e2739e6863d1e2fee1bb599e62eca8acfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"134f1f4867b3d99135dd79659f05b4e2739e6863d1e2fee1bb599e62eca8acfe","first_computed_at":"2026-07-05T05:11:02.478043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:02.478043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PiVJ9lhHk415e6gqlyX6rxj8fk7mObxxaIcI3VSAb6yY6iDmPl3MFu793I+qVXsZVgYquWNDi2tpVL+BkTcPDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:02.478403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.15131","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7208c6ff7b4bc1a328356ce030da415b10104c0ce4307c1c73e7d228da30c428","sha256:dbcb1396b06148d3d3e9dd9e3a6155f653dc1b4fc76fd8ac5a79a2f23deac114"],"state_sha256":"32cb28567adc0823a1e3dbd0037e4e2fba54c1c8f572853ea63ff4a2499f444a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TmX0lEeuzvSOd0bkSCCeJ3L6Hwx+ljR0IASavA3uu983N1/+EifPCZqRw8KjUYWn3FrryhGGk0wo23xKOE+YCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T16:06:53.435620Z","bundle_sha256":"99794545f7a660048f51241135683337be9712dc794e4f0f9fd8a051112eee44"}}