{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CSGJZB3A6HCBDJLV2SERRZRBKL","short_pith_number":"pith:CSGJZB3A","schema_version":"1.0","canonical_sha256":"148c9c8760f1c411a575d48918e62152f19b2deb5381d38602d9bb2b9729d079","source":{"kind":"arxiv","id":"2008.05809","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dipjyoti Paul, Muhammed PV Shifas, Yannis Pantazis, Yannis Stylianou","submitted_at":"2020-08-13T10:51:56Z","abstract_excerpt":"The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the presence of noise. Past studies have investigated style conversion in TTS synthesis, yet degraded synthesized quality often leads to worse intelligibility. To overcome such limitations, we proposed a novel transfer learning approach using Tacotron and WaveRNN based TTS synthesis. The proposed speech system exploits two modification strategies: (a) Lombard speak"},"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":"2008.05809","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-08-13T10:51:56Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"ca8fef1be60b4dadb4e7c9caf8a115f079066b68f234ae78ef55721837f4c91d","abstract_canon_sha256":"b08d6145d6ebcef8c63a8b7dae7bcac7f1ed4fb578887b56f351e6a02d5eade5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:57.692829Z","signature_b64":"AWadEEa+vqnvU/KJ1omSzAAWAxKIxGERcW9AbXO7ePpIaP+auh7cQI9ggVYcQT3jU8z4MCX/03zfCFUH7OSTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"148c9c8760f1c411a575d48918e62152f19b2deb5381d38602d9bb2b9729d079","last_reissued_at":"2026-07-05T01:26:57.692311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:57.692311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dipjyoti Paul, Muhammed PV Shifas, Yannis Pantazis, Yannis Stylianou","submitted_at":"2020-08-13T10:51:56Z","abstract_excerpt":"The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the presence of noise. Past studies have investigated style conversion in TTS synthesis, yet degraded synthesized quality often leads to worse intelligibility. To overcome such limitations, we proposed a novel transfer learning approach using Tacotron and WaveRNN based TTS synthesis. The proposed speech system exploits two modification strategies: (a) Lombard speak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05809","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/2008.05809/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":"2008.05809","created_at":"2026-07-05T01:26:57.692384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.05809v1","created_at":"2026-07-05T01:26:57.692384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05809","created_at":"2026-07-05T01:26:57.692384+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSGJZB3A6HCB","created_at":"2026-07-05T01:26:57.692384+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSGJZB3A6HCBDJLV","created_at":"2026-07-05T01:26:57.692384+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSGJZB3A","created_at":"2026-07-05T01:26:57.692384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09310","citing_title":"Voice Conversion for Lombard Speaking Style with Implicit and Explicit Acoustic Feature Conditioning","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CSGJZB3A6HCBDJLV2SERRZRBKL","json":"https://pith.science/pith/CSGJZB3A6HCBDJLV2SERRZRBKL.json","graph_json":"https://pith.science/api/pith-number/CSGJZB3A6HCBDJLV2SERRZRBKL/graph.json","events_json":"https://pith.science/api/pith-number/CSGJZB3A6HCBDJLV2SERRZRBKL/events.json","paper":"https://pith.science/paper/CSGJZB3A"},"agent_actions":{"view_html":"https://pith.science/pith/CSGJZB3A6HCBDJLV2SERRZRBKL","download_json":"https://pith.science/pith/CSGJZB3A6HCBDJLV2SERRZRBKL.json","view_paper":"https://pith.science/paper/CSGJZB3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.05809&json=true","fetch_graph":"https://pith.science/api/pith-number/CSGJZB3A6HCBDJLV2SERRZRBKL/graph.json","fetch_events":"https://pith.science/api/pith-number/CSGJZB3A6HCBDJLV2SERRZRBKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSGJZB3A6HCBDJLV2SERRZRBKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSGJZB3A6HCBDJLV2SERRZRBKL/action/storage_attestation","attest_author":"https://pith.science/pith/CSGJZB3A6HCBDJLV2SERRZRBKL/action/author_attestation","sign_citation":"https://pith.science/pith/CSGJZB3A6HCBDJLV2SERRZRBKL/action/citation_signature","submit_replication":"https://pith.science/pith/CSGJZB3A6HCBDJLV2SERRZRBKL/action/replication_record"}},"created_at":"2026-07-05T01:26:57.692384+00:00","updated_at":"2026-07-05T01:26:57.692384+00:00"}