{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3H44HVIM2MOLTVRTJUS7ET7N3A","short_pith_number":"pith:3H44HVIM","schema_version":"1.0","canonical_sha256":"d9f9c3d50cd31cb9d6334d25f24fedd818ff29dcd6d2613849844e60a7feda19","source":{"kind":"arxiv","id":"2007.00131","version":1},"attestation_state":"computed","paper":{"title":"Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Brian King, Gurpreet Chadha, Harish Mallidih, I-Fan Chen, Maarten Van Segbroeck, Roland Maas","submitted_at":"2020-06-30T22:19:53Z","abstract_excerpt":"Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending a stack of frequency-LSTM (FLSTM) layers to the time LSTM. These FLSTM layers can learn a more robust input feature to the time LSTM layers by modeling time-frequency correlations in the acoustic input signals. A drawback of FLSTM based architectures however is that they operate at a predefined, and tuned, window size and stride, referred to as 'view' in thi"},"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":"2007.00131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-30T22:19:53Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a495a384d7b05e75ae03d5ccdc8cdb03dcd078be18bcef384da87694c2597de8","abstract_canon_sha256":"859a7604359f151e915aab54cbd427e20ccad2f7324ed7176f733e02b95c8bd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:28.529967Z","signature_b64":"fQGMkZUKM5FgxkViey8CLL0dy3jr3u9yip49uvubq5NPmDSDRG9K0LYTDBMKOXFhUbe1fyNlKeoytf/jXKr+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9f9c3d50cd31cb9d6334d25f24fedd818ff29dcd6d2613849844e60a7feda19","last_reissued_at":"2026-07-05T01:15:28.529507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:28.529507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Brian King, Gurpreet Chadha, Harish Mallidih, I-Fan Chen, Maarten Van Segbroeck, Roland Maas","submitted_at":"2020-06-30T22:19:53Z","abstract_excerpt":"Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending a stack of frequency-LSTM (FLSTM) layers to the time LSTM. These FLSTM layers can learn a more robust input feature to the time LSTM layers by modeling time-frequency correlations in the acoustic input signals. A drawback of FLSTM based architectures however is that they operate at a predefined, and tuned, window size and stride, referred to as 'view' in thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00131","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/2007.00131/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":"2007.00131","created_at":"2026-07-05T01:15:28.529565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.00131v1","created_at":"2026-07-05T01:15:28.529565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00131","created_at":"2026-07-05T01:15:28.529565+00:00"},{"alias_kind":"pith_short_12","alias_value":"3H44HVIM2MOL","created_at":"2026-07-05T01:15:28.529565+00:00"},{"alias_kind":"pith_short_16","alias_value":"3H44HVIM2MOLTVRT","created_at":"2026-07-05T01:15:28.529565+00:00"},{"alias_kind":"pith_short_8","alias_value":"3H44HVIM","created_at":"2026-07-05T01:15:28.529565+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/3H44HVIM2MOLTVRTJUS7ET7N3A","json":"https://pith.science/pith/3H44HVIM2MOLTVRTJUS7ET7N3A.json","graph_json":"https://pith.science/api/pith-number/3H44HVIM2MOLTVRTJUS7ET7N3A/graph.json","events_json":"https://pith.science/api/pith-number/3H44HVIM2MOLTVRTJUS7ET7N3A/events.json","paper":"https://pith.science/paper/3H44HVIM"},"agent_actions":{"view_html":"https://pith.science/pith/3H44HVIM2MOLTVRTJUS7ET7N3A","download_json":"https://pith.science/pith/3H44HVIM2MOLTVRTJUS7ET7N3A.json","view_paper":"https://pith.science/paper/3H44HVIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.00131&json=true","fetch_graph":"https://pith.science/api/pith-number/3H44HVIM2MOLTVRTJUS7ET7N3A/graph.json","fetch_events":"https://pith.science/api/pith-number/3H44HVIM2MOLTVRTJUS7ET7N3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3H44HVIM2MOLTVRTJUS7ET7N3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3H44HVIM2MOLTVRTJUS7ET7N3A/action/storage_attestation","attest_author":"https://pith.science/pith/3H44HVIM2MOLTVRTJUS7ET7N3A/action/author_attestation","sign_citation":"https://pith.science/pith/3H44HVIM2MOLTVRTJUS7ET7N3A/action/citation_signature","submit_replication":"https://pith.science/pith/3H44HVIM2MOLTVRTJUS7ET7N3A/action/replication_record"}},"created_at":"2026-07-05T01:15:28.529565+00:00","updated_at":"2026-07-05T01:15:28.529565+00:00"}