{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E6MT2F3B32FMO37AUM4BNAXEFN","short_pith_number":"pith:E6MT2F3B","schema_version":"1.0","canonical_sha256":"27993d1761de8ac76fe0a3381682e42b7bae3bdd99c7e0c2563c00d66cab4160","source":{"kind":"arxiv","id":"2211.01948","version":3},"attestation_state":"computed","paper":{"title":"Efficiently Trained Low-Resource Mongolian Text-to-Speech System Based On FullConv-TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ziqi Liang","submitted_at":"2022-10-24T14:18:43Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) have become the standard modeling technique for sequence data, and are used in a number of novel text-to-speech models. However, training a TTS model including RNN components has certain requirements for GPU performance and takes a long time. In contrast, studies have shown that CNN-based sequence synthesis technology can greatly reduce training time in text-to-speech models while ensuring a certain performance due to its high parallelism. We propose a new text-to-speech system based on deep convolutional neural networks that does not employ any RNN components "},"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":"2211.01948","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-24T14:18:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a1c6b818fee199c8df51993fdf5eb7d4176011f24464092735bbb96e090cee4","abstract_canon_sha256":"7dfd0fa5f6cc9a646a15e7703dedc32ffad5847838b6133024d4dd39d6f6537b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:14.992470Z","signature_b64":"+V+gItE0T9FRoqYX4RX8N/CyPvOHKeJ6eukyR4YdvGCthHcN1S+vEFZhYKwZoJg7QsaqH4IdI/0BTDp5MUChDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27993d1761de8ac76fe0a3381682e42b7bae3bdd99c7e0c2563c00d66cab4160","last_reissued_at":"2026-07-05T06:01:14.991560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:14.991560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficiently Trained Low-Resource Mongolian Text-to-Speech System Based On FullConv-TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ziqi Liang","submitted_at":"2022-10-24T14:18:43Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) have become the standard modeling technique for sequence data, and are used in a number of novel text-to-speech models. However, training a TTS model including RNN components has certain requirements for GPU performance and takes a long time. In contrast, studies have shown that CNN-based sequence synthesis technology can greatly reduce training time in text-to-speech models while ensuring a certain performance due to its high parallelism. We propose a new text-to-speech system based on deep convolutional neural networks that does not employ any RNN components "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01948","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/2211.01948/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":"2211.01948","created_at":"2026-07-05T06:01:14.991701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01948v3","created_at":"2026-07-05T06:01:14.991701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01948","created_at":"2026-07-05T06:01:14.991701+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6MT2F3B32FM","created_at":"2026-07-05T06:01:14.991701+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6MT2F3B32FMO37A","created_at":"2026-07-05T06:01:14.991701+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6MT2F3B","created_at":"2026-07-05T06:01:14.991701+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/E6MT2F3B32FMO37AUM4BNAXEFN","json":"https://pith.science/pith/E6MT2F3B32FMO37AUM4BNAXEFN.json","graph_json":"https://pith.science/api/pith-number/E6MT2F3B32FMO37AUM4BNAXEFN/graph.json","events_json":"https://pith.science/api/pith-number/E6MT2F3B32FMO37AUM4BNAXEFN/events.json","paper":"https://pith.science/paper/E6MT2F3B"},"agent_actions":{"view_html":"https://pith.science/pith/E6MT2F3B32FMO37AUM4BNAXEFN","download_json":"https://pith.science/pith/E6MT2F3B32FMO37AUM4BNAXEFN.json","view_paper":"https://pith.science/paper/E6MT2F3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01948&json=true","fetch_graph":"https://pith.science/api/pith-number/E6MT2F3B32FMO37AUM4BNAXEFN/graph.json","fetch_events":"https://pith.science/api/pith-number/E6MT2F3B32FMO37AUM4BNAXEFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6MT2F3B32FMO37AUM4BNAXEFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6MT2F3B32FMO37AUM4BNAXEFN/action/storage_attestation","attest_author":"https://pith.science/pith/E6MT2F3B32FMO37AUM4BNAXEFN/action/author_attestation","sign_citation":"https://pith.science/pith/E6MT2F3B32FMO37AUM4BNAXEFN/action/citation_signature","submit_replication":"https://pith.science/pith/E6MT2F3B32FMO37AUM4BNAXEFN/action/replication_record"}},"created_at":"2026-07-05T06:01:14.991701+00:00","updated_at":"2026-07-05T06:01:14.991701+00:00"}