{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VUPDHS5LSY4FGK6E72OX7PM6FV","short_pith_number":"pith:VUPDHS5L","schema_version":"1.0","canonical_sha256":"ad1e33cbab9638532bc4fe9d7fbd9e2d41f01df3a313e2f7f96b5f337e49c3ac","source":{"kind":"arxiv","id":"2306.06954","version":1},"attestation_state":"computed","paper":{"title":"Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Belen Alastruey, Jahn Heymann, Lukas Drude, Simon Wiesler","submitted_at":"2023-06-12T08:37:36Z","abstract_excerpt":"Convolutional frontends are a typical choice for Transformer-based automatic speech recognition to preprocess the spectrogram, reduce its sequence length, and combine local information in time and frequency similarly. However, the width and height of an audio spectrogram denote different information, e.g., due to reverberation as well as the articulatory system, the time axis has a clear left-to-right dependency. On the contrary, vowels and consonants demonstrate very different patterns and occupy almost disjoint frequency ranges. Therefore, we hypothesize, global attention over frequencies is"},"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":"2306.06954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-12T08:37:36Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"922925c32074a8bff11c2c1d148195e5c4b609addfd22dad5e956cd7490d02f2","abstract_canon_sha256":"82714b9da0115525e843e1e8e37573a13d626f384c7215f8fe6e6cc73efe2ad8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:46.069039Z","signature_b64":"/0LuWTOiSWEuX9SQCghlmUq6W30a0GWM9AuSn0T0QL3u6iSk06+I7whM7cCHybbPX9WtGsQzKUDMIP1RUXyuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad1e33cbab9638532bc4fe9d7fbd9e2d41f01df3a313e2f7f96b5f337e49c3ac","last_reissued_at":"2026-07-05T06:19:46.068577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:46.068577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Belen Alastruey, Jahn Heymann, Lukas Drude, Simon Wiesler","submitted_at":"2023-06-12T08:37:36Z","abstract_excerpt":"Convolutional frontends are a typical choice for Transformer-based automatic speech recognition to preprocess the spectrogram, reduce its sequence length, and combine local information in time and frequency similarly. However, the width and height of an audio spectrogram denote different information, e.g., due to reverberation as well as the articulatory system, the time axis has a clear left-to-right dependency. On the contrary, vowels and consonants demonstrate very different patterns and occupy almost disjoint frequency ranges. Therefore, we hypothesize, global attention over frequencies is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06954","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/2306.06954/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":"2306.06954","created_at":"2026-07-05T06:19:46.068635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06954v1","created_at":"2026-07-05T06:19:46.068635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06954","created_at":"2026-07-05T06:19:46.068635+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUPDHS5LSY4F","created_at":"2026-07-05T06:19:46.068635+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUPDHS5LSY4FGK6E","created_at":"2026-07-05T06:19:46.068635+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUPDHS5L","created_at":"2026-07-05T06:19:46.068635+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/VUPDHS5LSY4FGK6E72OX7PM6FV","json":"https://pith.science/pith/VUPDHS5LSY4FGK6E72OX7PM6FV.json","graph_json":"https://pith.science/api/pith-number/VUPDHS5LSY4FGK6E72OX7PM6FV/graph.json","events_json":"https://pith.science/api/pith-number/VUPDHS5LSY4FGK6E72OX7PM6FV/events.json","paper":"https://pith.science/paper/VUPDHS5L"},"agent_actions":{"view_html":"https://pith.science/pith/VUPDHS5LSY4FGK6E72OX7PM6FV","download_json":"https://pith.science/pith/VUPDHS5LSY4FGK6E72OX7PM6FV.json","view_paper":"https://pith.science/paper/VUPDHS5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06954&json=true","fetch_graph":"https://pith.science/api/pith-number/VUPDHS5LSY4FGK6E72OX7PM6FV/graph.json","fetch_events":"https://pith.science/api/pith-number/VUPDHS5LSY4FGK6E72OX7PM6FV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUPDHS5LSY4FGK6E72OX7PM6FV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUPDHS5LSY4FGK6E72OX7PM6FV/action/storage_attestation","attest_author":"https://pith.science/pith/VUPDHS5LSY4FGK6E72OX7PM6FV/action/author_attestation","sign_citation":"https://pith.science/pith/VUPDHS5LSY4FGK6E72OX7PM6FV/action/citation_signature","submit_replication":"https://pith.science/pith/VUPDHS5LSY4FGK6E72OX7PM6FV/action/replication_record"}},"created_at":"2026-07-05T06:19:46.068635+00:00","updated_at":"2026-07-05T06:19:46.068635+00:00"}