{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:36QXD2SZ26MPSRW24AGY7PEBHH","short_pith_number":"pith:36QXD2SZ","schema_version":"1.0","canonical_sha256":"dfa171ea59d798f946dae00d8fbc8139e413d38772ab3b3a7133bf04035c2e7b","source":{"kind":"arxiv","id":"1803.04840","version":1},"attestation_state":"computed","paper":{"title":"Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bert Moons, Marian Verhelst, Matthijs Van keirsbilck","submitted_at":"2018-03-13T14:35:00Z","abstract_excerpt":"Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video simultaneously - significantly enhances the performance of such systems, especially in noisy environments. This work presents the design of such an audio-visual system for Automated Speech Recognition, taking memory and computation requirements into account. First, a Long-Short-Term-Memory neural network for acoustic speech recognition is designed. Second, Convolutiona"},"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":"1803.04840","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-13T14:35:00Z","cross_cats_sorted":[],"title_canon_sha256":"eacc1e7db22f24af372697e1daf37e6c3bff062f3d24d7b4aa39ffc5a65eb195","abstract_canon_sha256":"a1e2adf97134c613759dbcce961793729aab86933dd78ee11398b9dd4bfd2e4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:17.601913Z","signature_b64":"rn0Mki6+npjQX8lXNEiOZp/znKechqHVhINx0Scszo13Z5R/XGNl96gOfqElINJFiEYSrPl6CdZUM8wLKotZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfa171ea59d798f946dae00d8fbc8139e413d38772ab3b3a7133bf04035c2e7b","last_reissued_at":"2026-05-18T00:21:17.601438Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:17.601438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bert Moons, Marian Verhelst, Matthijs Van keirsbilck","submitted_at":"2018-03-13T14:35:00Z","abstract_excerpt":"Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video simultaneously - significantly enhances the performance of such systems, especially in noisy environments. This work presents the design of such an audio-visual system for Automated Speech Recognition, taking memory and computation requirements into account. First, a Long-Short-Term-Memory neural network for acoustic speech recognition is designed. Second, Convolutiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04840","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":""},"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":"1803.04840","created_at":"2026-05-18T00:21:17.601504+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.04840v1","created_at":"2026-05-18T00:21:17.601504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04840","created_at":"2026-05-18T00:21:17.601504+00:00"},{"alias_kind":"pith_short_12","alias_value":"36QXD2SZ26MP","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"36QXD2SZ26MPSRW2","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"36QXD2SZ","created_at":"2026-05-18T12:32:02.567920+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/36QXD2SZ26MPSRW24AGY7PEBHH","json":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH.json","graph_json":"https://pith.science/api/pith-number/36QXD2SZ26MPSRW24AGY7PEBHH/graph.json","events_json":"https://pith.science/api/pith-number/36QXD2SZ26MPSRW24AGY7PEBHH/events.json","paper":"https://pith.science/paper/36QXD2SZ"},"agent_actions":{"view_html":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH","download_json":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH.json","view_paper":"https://pith.science/paper/36QXD2SZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.04840&json=true","fetch_graph":"https://pith.science/api/pith-number/36QXD2SZ26MPSRW24AGY7PEBHH/graph.json","fetch_events":"https://pith.science/api/pith-number/36QXD2SZ26MPSRW24AGY7PEBHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH/action/storage_attestation","attest_author":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH/action/author_attestation","sign_citation":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH/action/citation_signature","submit_replication":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH/action/replication_record"}},"created_at":"2026-05-18T00:21:17.601504+00:00","updated_at":"2026-05-18T00:21:17.601504+00:00"}