{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VJPZIDAEJVQF7677MFLI4NYILZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7e5939e5d4942f0ba277eb7cf33a7b8e26e8c2da59230104ea0ed5cb1a9423ed","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-05-12T19:32:24Z","title_canon_sha256":"c225598442a759a311b12422b6ce82fd3d762599852120463930e5e70cd95621"},"schema_version":"1.0","source":{"id":"2105.05920","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05920","created_at":"2026-07-05T02:40:35Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05920v2","created_at":"2026-07-05T02:40:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05920","created_at":"2026-07-05T02:40:35Z"},{"alias_kind":"pith_short_12","alias_value":"VJPZIDAEJVQF","created_at":"2026-07-05T02:40:35Z"},{"alias_kind":"pith_short_16","alias_value":"VJPZIDAEJVQF7677","created_at":"2026-07-05T02:40:35Z"},{"alias_kind":"pith_short_8","alias_value":"VJPZIDAE","created_at":"2026-07-05T02:40:35Z"}],"graph_snapshots":[{"event_id":"sha256:31ea826107b1e5a4fb0378c2055c0925f3383dbe07a513b2538ced8cafb41878","target":"graph","created_at":"2026-07-05T02:40:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2105.05920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Attention-based beamformers have recently been shown to be effective for multi-channel speech recognition. However, they are less capable at capturing local information. In this work, we propose a 2D Conv-Attention module which combines convolution neural networks with attention for beamforming. We apply self- and cross-attention to explicitly model the correlations within and between the input channels. The end-to-end 2D Conv-Attention model is compared with a multi-head self-attention and superdirective-based neural beamformers. We train and evaluate on an in-house multi-channel dataset. The","authors_text":"Bhargav Pulugundla, Brian King, Gokce Keskin, Harish Mallidi, Jasha Droppo, Minhua Wu, Roland Maas, Yang Gao","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-05-12T19:32:24Z","title":"Attention-based Neural Beamforming Layers for Multi-channel Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05920","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:77dab80977c211f0148d1f33f98108142e6f11d59e1e89cbe6218f0b1df57730","target":"record","created_at":"2026-07-05T02:40:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7e5939e5d4942f0ba277eb7cf33a7b8e26e8c2da59230104ea0ed5cb1a9423ed","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-05-12T19:32:24Z","title_canon_sha256":"c225598442a759a311b12422b6ce82fd3d762599852120463930e5e70cd95621"},"schema_version":"1.0","source":{"id":"2105.05920","kind":"arxiv","version":2}},"canonical_sha256":"aa5f940c044d605ffbff61568e37085e696a08db6f5d44ff592a5e786a1caf5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa5f940c044d605ffbff61568e37085e696a08db6f5d44ff592a5e786a1caf5e","first_computed_at":"2026-07-05T02:40:35.674614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:35.674614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LDbqzfKZswydLvxEPLsy6BSRqJItq0qKZdabq2pwZ7bgb9fNKLjCDuf/GmO47rY9t2bABHcApKtSLeWeaggDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:35.675003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.05920","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77dab80977c211f0148d1f33f98108142e6f11d59e1e89cbe6218f0b1df57730","sha256:31ea826107b1e5a4fb0378c2055c0925f3383dbe07a513b2538ced8cafb41878"],"state_sha256":"d4b78c9d86af5a0efc132068dc9588e51282535f3a7ca1b1b2ddeae5d807be20"}