{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GR3UHIA5E4ZHSDEOZKDB36MI7E","short_pith_number":"pith:GR3UHIA5","schema_version":"1.0","canonical_sha256":"347743a01d2732790c8eca861df988f9263ee3b4bc5d758efd7d84f7fd9df85c","source":{"kind":"arxiv","id":"2303.11607","version":2},"attestation_state":"computed","paper":{"title":"Transformers in Speech Processing: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aun Zaidi, Fahad Shamshad, Heriberto Cuayahuitl, Junaid Qadir, Moazzam Shoukat, Muhammad Usama, Siddique Latif","submitted_at":"2023-03-21T06:00:39Z","abstract_excerpt":"The remarkable success of transformers in the field of natural language processing has sparked the interest of the speech-processing community, leading to an exploration of their potential for modeling long-range dependencies within speech sequences. Recently, transformers have gained prominence across various speech-related domains, including automatic speech recognition, speech synthesis, speech translation, speech para-linguistics, speech enhancement, spoken dialogue systems, and numerous multimodal applications. In this paper, we present a comprehensive survey that aims to bridge research "},"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":"2303.11607","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-21T06:00:39Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"adb28008b3ac0bbaebdab95f1f1277ee85d98224737dfce5e8ff145356f99382","abstract_canon_sha256":"4e5a0523123e457974115f5e26f45ca721a5be542ce1e1690fa5ff05fef8b746"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:35.981605Z","signature_b64":"FpEf2SgfgaiGmZrR+jdHiWQrO4loYe9bpgZMV+2eKIuYj+uEsRYewrHY+nx4JzQaNJ7eKBj+LDdh/nk3Z+eRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"347743a01d2732790c8eca861df988f9263ee3b4bc5d758efd7d84f7fd9df85c","last_reissued_at":"2026-07-05T11:15:35.981078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:35.981078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers in Speech Processing: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aun Zaidi, Fahad Shamshad, Heriberto Cuayahuitl, Junaid Qadir, Moazzam Shoukat, Muhammad Usama, Siddique Latif","submitted_at":"2023-03-21T06:00:39Z","abstract_excerpt":"The remarkable success of transformers in the field of natural language processing has sparked the interest of the speech-processing community, leading to an exploration of their potential for modeling long-range dependencies within speech sequences. Recently, transformers have gained prominence across various speech-related domains, including automatic speech recognition, speech synthesis, speech translation, speech para-linguistics, speech enhancement, spoken dialogue systems, and numerous multimodal applications. In this paper, we present a comprehensive survey that aims to bridge research "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11607","kind":"arxiv","version":2},"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/2303.11607/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":"2303.11607","created_at":"2026-07-05T11:15:35.981150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11607v2","created_at":"2026-07-05T11:15:35.981150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11607","created_at":"2026-07-05T11:15:35.981150+00:00"},{"alias_kind":"pith_short_12","alias_value":"GR3UHIA5E4ZH","created_at":"2026-07-05T11:15:35.981150+00:00"},{"alias_kind":"pith_short_16","alias_value":"GR3UHIA5E4ZHSDEO","created_at":"2026-07-05T11:15:35.981150+00:00"},{"alias_kind":"pith_short_8","alias_value":"GR3UHIA5","created_at":"2026-07-05T11:15:35.981150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00077","citing_title":"Improved Belief-Attention in Vision Task","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17152","citing_title":"Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages","ref_index":230,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17653","citing_title":"LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19028","citing_title":"Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors","ref_index":231,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GR3UHIA5E4ZHSDEOZKDB36MI7E","json":"https://pith.science/pith/GR3UHIA5E4ZHSDEOZKDB36MI7E.json","graph_json":"https://pith.science/api/pith-number/GR3UHIA5E4ZHSDEOZKDB36MI7E/graph.json","events_json":"https://pith.science/api/pith-number/GR3UHIA5E4ZHSDEOZKDB36MI7E/events.json","paper":"https://pith.science/paper/GR3UHIA5"},"agent_actions":{"view_html":"https://pith.science/pith/GR3UHIA5E4ZHSDEOZKDB36MI7E","download_json":"https://pith.science/pith/GR3UHIA5E4ZHSDEOZKDB36MI7E.json","view_paper":"https://pith.science/paper/GR3UHIA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11607&json=true","fetch_graph":"https://pith.science/api/pith-number/GR3UHIA5E4ZHSDEOZKDB36MI7E/graph.json","fetch_events":"https://pith.science/api/pith-number/GR3UHIA5E4ZHSDEOZKDB36MI7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GR3UHIA5E4ZHSDEOZKDB36MI7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GR3UHIA5E4ZHSDEOZKDB36MI7E/action/storage_attestation","attest_author":"https://pith.science/pith/GR3UHIA5E4ZHSDEOZKDB36MI7E/action/author_attestation","sign_citation":"https://pith.science/pith/GR3UHIA5E4ZHSDEOZKDB36MI7E/action/citation_signature","submit_replication":"https://pith.science/pith/GR3UHIA5E4ZHSDEOZKDB36MI7E/action/replication_record"}},"created_at":"2026-07-05T11:15:35.981150+00:00","updated_at":"2026-07-05T11:15:35.981150+00:00"}