{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CNHR6SDHWPMZCNO5PFSZ6BNU4J","short_pith_number":"pith:CNHR6SDH","schema_version":"1.0","canonical_sha256":"134f1f4867b3d99135dd79659f05b4e2739e6863d1e2fee1bb599e62eca8acfe","source":{"kind":"arxiv","id":"2210.15131","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.15131","created_at":"2026-07-05T05:11:02.478099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15131v1","created_at":"2026-07-05T05:11:02.478099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15131","created_at":"2026-07-05T05:11:02.478099+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNHR6SDHWPMZ","created_at":"2026-07-05T05:11:02.478099+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNHR6SDHWPMZCNO5","created_at":"2026-07-05T05:11:02.478099+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNHR6SDH","created_at":"2026-07-05T05:11:02.478099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J","json":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J.json","graph_json":"https://pith.science/api/pith-number/CNHR6SDHWPMZCNO5PFSZ6BNU4J/graph.json","events_json":"https://pith.science/api/pith-number/CNHR6SDHWPMZCNO5PFSZ6BNU4J/events.json","paper":"https://pith.science/paper/CNHR6SDH"},"agent_actions":{"view_html":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J","download_json":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J.json","view_paper":"https://pith.science/paper/CNHR6SDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15131&json=true","fetch_graph":"https://pith.science/api/pith-number/CNHR6SDHWPMZCNO5PFSZ6BNU4J/graph.json","fetch_events":"https://pith.science/api/pith-number/CNHR6SDHWPMZCNO5PFSZ6BNU4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/action/storage_attestation","attest_author":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/action/author_attestation","sign_citation":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/action/citation_signature","submit_replication":"https://pith.science/pith/CNHR6SDHWPMZCNO5PFSZ6BNU4J/action/replication_record"}},"created_at":"2026-07-05T05:11:02.478099+00:00","updated_at":"2026-07-05T05:11:02.478099+00:00"}