{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7WGAREKZJENKG4TYPCZ2ZEPCCO","short_pith_number":"pith:7WGAREKZ","schema_version":"1.0","canonical_sha256":"fd8c089159491aa3727878b3ac91e213a7f531e936167e56ee3ec8e5c0334559","source":{"kind":"arxiv","id":"2004.09347","version":3},"attestation_state":"computed","paper":{"title":"End-to-End Whisper to Natural Speech Conversion using Modified Transformer Network","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Abhishek Niranjan, M Ali Basha Shaik, Mukesh Sharma, Sai Bharath Chandra Gutha","submitted_at":"2020-04-20T14:47:46Z","abstract_excerpt":"Machine recognition of an atypical speech like whispered speech, is a challenging task. We introduce whisper-to-natural-speech conversion using sequence-to-sequence approach by proposing enhanced transformer architecture, which uses both parallel and non-parallel data. We investigate different features like Mel frequency cepstral coefficients and smoothed spectral features. The proposed networks are trained end-to-end using supervised approach for feature-to-feature transformation. Further, we also investigate the effectiveness of embedded auxillary decoder used after N encoder sub-layers, tra"},"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":"2004.09347","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2020-04-20T14:47:46Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"12721748586b9752c5e69370444c21e76379420ec237100bd9988c6497ed0366","abstract_canon_sha256":"97aeaf2ac00548df8ce2bbc26c45288c092e3bd2c4eb7de1f7a9fc2ad60e6aac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:49.075195Z","signature_b64":"KWAUAP6GWVi5XzW2r+qbiIwjy5OouR50pNSjF7rHq1tweSrGL1+3Au/FrRR0RMci3NoYywJnM9ZNyVSht1zNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd8c089159491aa3727878b3ac91e213a7f531e936167e56ee3ec8e5c0334559","last_reissued_at":"2026-07-05T02:28:49.074809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:49.074809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Whisper to Natural Speech Conversion using Modified Transformer Network","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Abhishek Niranjan, M Ali Basha Shaik, Mukesh Sharma, Sai Bharath Chandra Gutha","submitted_at":"2020-04-20T14:47:46Z","abstract_excerpt":"Machine recognition of an atypical speech like whispered speech, is a challenging task. We introduce whisper-to-natural-speech conversion using sequence-to-sequence approach by proposing enhanced transformer architecture, which uses both parallel and non-parallel data. We investigate different features like Mel frequency cepstral coefficients and smoothed spectral features. The proposed networks are trained end-to-end using supervised approach for feature-to-feature transformation. Further, we also investigate the effectiveness of embedded auxillary decoder used after N encoder sub-layers, tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09347","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/2004.09347/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":"2004.09347","created_at":"2026-07-05T02:28:49.074870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.09347v3","created_at":"2026-07-05T02:28:49.074870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09347","created_at":"2026-07-05T02:28:49.074870+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WGAREKZJENK","created_at":"2026-07-05T02:28:49.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WGAREKZJENKG4TY","created_at":"2026-07-05T02:28:49.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WGAREKZ","created_at":"2026-07-05T02:28:49.074870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06675","citing_title":"Accurate analysis of the pitch pulse-based magnitude/phase structure of natural vowels and assessment of three lightweight time/frequency voicing restoration methods","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WGAREKZJENKG4TYPCZ2ZEPCCO","json":"https://pith.science/pith/7WGAREKZJENKG4TYPCZ2ZEPCCO.json","graph_json":"https://pith.science/api/pith-number/7WGAREKZJENKG4TYPCZ2ZEPCCO/graph.json","events_json":"https://pith.science/api/pith-number/7WGAREKZJENKG4TYPCZ2ZEPCCO/events.json","paper":"https://pith.science/paper/7WGAREKZ"},"agent_actions":{"view_html":"https://pith.science/pith/7WGAREKZJENKG4TYPCZ2ZEPCCO","download_json":"https://pith.science/pith/7WGAREKZJENKG4TYPCZ2ZEPCCO.json","view_paper":"https://pith.science/paper/7WGAREKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.09347&json=true","fetch_graph":"https://pith.science/api/pith-number/7WGAREKZJENKG4TYPCZ2ZEPCCO/graph.json","fetch_events":"https://pith.science/api/pith-number/7WGAREKZJENKG4TYPCZ2ZEPCCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WGAREKZJENKG4TYPCZ2ZEPCCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WGAREKZJENKG4TYPCZ2ZEPCCO/action/storage_attestation","attest_author":"https://pith.science/pith/7WGAREKZJENKG4TYPCZ2ZEPCCO/action/author_attestation","sign_citation":"https://pith.science/pith/7WGAREKZJENKG4TYPCZ2ZEPCCO/action/citation_signature","submit_replication":"https://pith.science/pith/7WGAREKZJENKG4TYPCZ2ZEPCCO/action/replication_record"}},"created_at":"2026-07-05T02:28:49.074870+00:00","updated_at":"2026-07-05T02:28:49.074870+00:00"}