{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7UZGS5WKOXUFNDT3KGJRNM6I4Q","short_pith_number":"pith:7UZGS5WK","schema_version":"1.0","canonical_sha256":"fd326976ca75e8568e7b519316b3c8e439e3d9640883bea10949c84db55554b8","source":{"kind":"arxiv","id":"2108.00500","version":1},"attestation_state":"computed","paper":{"title":"End to End Bangla Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arif Ahmad, M. Shahidur Rahman, Prithwiraj Bhattacharjee, Rajan Saha Raju","submitted_at":"2021-08-01T17:16:03Z","abstract_excerpt":"Text-to-Speech (TTS) system is a system where speech is synthesized from a given text following any particular approach. Concatenative synthesis, Hidden Markov Model (HMM) based synthesis, Deep Learning (DL) based synthesis with multiple building blocks, etc. are the main approaches for implementing a TTS system. Here, we are presenting our deep learning-based end-to-end Bangla speech synthesis system. It has been implemented with minimal human annotation using only 3 major components (Encoder, Decoder, Post-processing net including waveform synthesis). It does not require any frontend preproc"},"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":"2108.00500","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-08-01T17:16:03Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"2d85d0fe22974e27f765a75834af70c9f3afd2acb8438809cc9af159fe70c472","abstract_canon_sha256":"6f4610ea968ca33be5decd712c2d69c3bc77a9c90cd3826128d056d1503f0736"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:23.853057Z","signature_b64":"MIHkH6IWd9uem++7esG7hsYWKLnZR0AmBYSpIEAWHT7/SR2QlNXM5g433XuNgqbHDuIzDD+llRCLjwpcdIlZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd326976ca75e8568e7b519316b3c8e439e3d9640883bea10949c84db55554b8","last_reissued_at":"2026-07-05T03:02:23.852654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:23.852654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End to End Bangla Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arif Ahmad, M. Shahidur Rahman, Prithwiraj Bhattacharjee, Rajan Saha Raju","submitted_at":"2021-08-01T17:16:03Z","abstract_excerpt":"Text-to-Speech (TTS) system is a system where speech is synthesized from a given text following any particular approach. Concatenative synthesis, Hidden Markov Model (HMM) based synthesis, Deep Learning (DL) based synthesis with multiple building blocks, etc. are the main approaches for implementing a TTS system. Here, we are presenting our deep learning-based end-to-end Bangla speech synthesis system. It has been implemented with minimal human annotation using only 3 major components (Encoder, Decoder, Post-processing net including waveform synthesis). It does not require any frontend preproc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00500","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/2108.00500/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":"2108.00500","created_at":"2026-07-05T03:02:23.852710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00500v1","created_at":"2026-07-05T03:02:23.852710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00500","created_at":"2026-07-05T03:02:23.852710+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UZGS5WKOXUF","created_at":"2026-07-05T03:02:23.852710+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UZGS5WKOXUFNDT3","created_at":"2026-07-05T03:02:23.852710+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UZGS5WK","created_at":"2026-07-05T03:02:23.852710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10879","citing_title":"BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardization","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UZGS5WKOXUFNDT3KGJRNM6I4Q","json":"https://pith.science/pith/7UZGS5WKOXUFNDT3KGJRNM6I4Q.json","graph_json":"https://pith.science/api/pith-number/7UZGS5WKOXUFNDT3KGJRNM6I4Q/graph.json","events_json":"https://pith.science/api/pith-number/7UZGS5WKOXUFNDT3KGJRNM6I4Q/events.json","paper":"https://pith.science/paper/7UZGS5WK"},"agent_actions":{"view_html":"https://pith.science/pith/7UZGS5WKOXUFNDT3KGJRNM6I4Q","download_json":"https://pith.science/pith/7UZGS5WKOXUFNDT3KGJRNM6I4Q.json","view_paper":"https://pith.science/paper/7UZGS5WK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00500&json=true","fetch_graph":"https://pith.science/api/pith-number/7UZGS5WKOXUFNDT3KGJRNM6I4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/7UZGS5WKOXUFNDT3KGJRNM6I4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UZGS5WKOXUFNDT3KGJRNM6I4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UZGS5WKOXUFNDT3KGJRNM6I4Q/action/storage_attestation","attest_author":"https://pith.science/pith/7UZGS5WKOXUFNDT3KGJRNM6I4Q/action/author_attestation","sign_citation":"https://pith.science/pith/7UZGS5WKOXUFNDT3KGJRNM6I4Q/action/citation_signature","submit_replication":"https://pith.science/pith/7UZGS5WKOXUFNDT3KGJRNM6I4Q/action/replication_record"}},"created_at":"2026-07-05T03:02:23.852710+00:00","updated_at":"2026-07-05T03:02:23.852710+00:00"}