{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2IWQ3EKXNEAX6CB7QCB5JC72YE","short_pith_number":"pith:2IWQ3EKX","schema_version":"1.0","canonical_sha256":"d22d0d915769017f083f8083d48bfac11b3224749f7c25ecd104acb8c21af060","source":{"kind":"arxiv","id":"2309.10795","version":1},"attestation_state":"computed","paper":{"title":"Exploring Speech Enhancement for Low-resource Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Changhan Wang, Gael Le Lan, Kohei Saijo, Ning Dong, Sravya Popuri, Vikas Chandra, Xiaohui Zhang, Yangyang Shi, Zhaoheng Ni","submitted_at":"2023-09-19T17:42:57Z","abstract_excerpt":"High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive. Applying speech enhancement on Automatic Speech Recognition (ASR) corpus mitigates the issue by augmenting the training data, while how the nonlinear speech distortion brought by speech enhancement models affects TTS training still needs to be investigated. In this paper, we train a TF-GridNet speech enhancement model and apply it to low-resource datasets that were collected for the ASR task, then train a discret"},"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":"2309.10795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T17:42:57Z","cross_cats_sorted":[],"title_canon_sha256":"c70f9bb3a65af1a65983cc755270074e640df0d770cb6caec7782798d4343a33","abstract_canon_sha256":"1050e362b5a1240b4214acf9b3694f86c5f37297b2a384a3c68099fc41c0c29a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:17.278037Z","signature_b64":"pDgGposA1wXptJ61BDXBYOZEV2Cya0Q3I4w7+a3KdEmcJhXLmLUaxxlOnDQY0PE0uHTQHiROcPGIdG4ul2iCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d22d0d915769017f083f8083d48bfac11b3224749f7c25ecd104acb8c21af060","last_reissued_at":"2026-07-05T06:52:17.277558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:17.277558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Speech Enhancement for Low-resource Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Changhan Wang, Gael Le Lan, Kohei Saijo, Ning Dong, Sravya Popuri, Vikas Chandra, Xiaohui Zhang, Yangyang Shi, Zhaoheng Ni","submitted_at":"2023-09-19T17:42:57Z","abstract_excerpt":"High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive. Applying speech enhancement on Automatic Speech Recognition (ASR) corpus mitigates the issue by augmenting the training data, while how the nonlinear speech distortion brought by speech enhancement models affects TTS training still needs to be investigated. In this paper, we train a TF-GridNet speech enhancement model and apply it to low-resource datasets that were collected for the ASR task, then train a discret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10795","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/2309.10795/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":"2309.10795","created_at":"2026-07-05T06:52:17.277616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10795v1","created_at":"2026-07-05T06:52:17.277616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10795","created_at":"2026-07-05T06:52:17.277616+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IWQ3EKXNEAX","created_at":"2026-07-05T06:52:17.277616+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IWQ3EKXNEAX6CB7","created_at":"2026-07-05T06:52:17.277616+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IWQ3EKX","created_at":"2026-07-05T06:52:17.277616+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/2IWQ3EKXNEAX6CB7QCB5JC72YE","json":"https://pith.science/pith/2IWQ3EKXNEAX6CB7QCB5JC72YE.json","graph_json":"https://pith.science/api/pith-number/2IWQ3EKXNEAX6CB7QCB5JC72YE/graph.json","events_json":"https://pith.science/api/pith-number/2IWQ3EKXNEAX6CB7QCB5JC72YE/events.json","paper":"https://pith.science/paper/2IWQ3EKX"},"agent_actions":{"view_html":"https://pith.science/pith/2IWQ3EKXNEAX6CB7QCB5JC72YE","download_json":"https://pith.science/pith/2IWQ3EKXNEAX6CB7QCB5JC72YE.json","view_paper":"https://pith.science/paper/2IWQ3EKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10795&json=true","fetch_graph":"https://pith.science/api/pith-number/2IWQ3EKXNEAX6CB7QCB5JC72YE/graph.json","fetch_events":"https://pith.science/api/pith-number/2IWQ3EKXNEAX6CB7QCB5JC72YE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IWQ3EKXNEAX6CB7QCB5JC72YE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IWQ3EKXNEAX6CB7QCB5JC72YE/action/storage_attestation","attest_author":"https://pith.science/pith/2IWQ3EKXNEAX6CB7QCB5JC72YE/action/author_attestation","sign_citation":"https://pith.science/pith/2IWQ3EKXNEAX6CB7QCB5JC72YE/action/citation_signature","submit_replication":"https://pith.science/pith/2IWQ3EKXNEAX6CB7QCB5JC72YE/action/replication_record"}},"created_at":"2026-07-05T06:52:17.277616+00:00","updated_at":"2026-07-05T06:52:17.277616+00:00"}