{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OEUBZUP2K4ABNLRHIZ7UK4W2YL","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":"4a67dca10e01625be298ade247fe08dbc78ba4fea1579b2c5938b3b06b671af9","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-05-04T02:25:41Z","title_canon_sha256":"7c82e4bc2d94cda101eb51a36860acd71ae2548dae3e04eb895d15723e90dbd0"},"schema_version":"1.0","source":{"id":"2105.01254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.01254","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2105.01254v1","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01254","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"OEUBZUP2K4AB","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"OEUBZUP2K4ABNLRH","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"OEUBZUP2","created_at":"2026-07-05T02:37:15Z"}],"graph_snapshots":[{"event_id":"sha256:ae44127fca68e95893c3925039eb1cc91796fdcc2c1011c00db0fb96bccd2880","target":"graph","created_at":"2026-07-05T02:37:15Z","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/2105.01254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a streaming end-to-end speech recognition model based on Monotonic Chunkwise Attention (MoCha) jointly trained with enhancement layers. Even though the MoCha attention enables streaming speech recognition with recognition accuracy comparable to a full attention-based approach, training this model is sensitive to various factors such as the difficulty of training examples, hyper-parameters, and so on. Because of these issues, speech recognition accuracy of a MoCha-based model for clean speech drops significantly when a multi-style training approach is applied. Inspired","authors_text":"Abhinav Garg, Changwoo Han, Chanwoo Kim, Dhananjaya Gowda, Seongkyu Mun","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-05-04T02:25:41Z","title":"Streaming end-to-end speech recognition with jointly trained neural feature enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01254","kind":"arxiv","version":1},"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":"sha256:584c433801f14580c5b0db471eb252f56f7ced1c346d9647b51ccb00d510e979","target":"record","created_at":"2026-07-05T02:37:15Z","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":"4a67dca10e01625be298ade247fe08dbc78ba4fea1579b2c5938b3b06b671af9","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-05-04T02:25:41Z","title_canon_sha256":"7c82e4bc2d94cda101eb51a36860acd71ae2548dae3e04eb895d15723e90dbd0"},"schema_version":"1.0","source":{"id":"2105.01254","kind":"arxiv","version":1}},"canonical_sha256":"71281cd1fa570016ae27467f4572dac2f22df1a90d0624d22f14106ccff8dd7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71281cd1fa570016ae27467f4572dac2f22df1a90d0624d22f14106ccff8dd7e","first_computed_at":"2026-07-05T02:37:15.150336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:15.150336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wvCsBXnJ0Igegs4KyL2Ez7qWoizWN2Vo4Z4hK75/yE30zqduMUR8mLL4y9liDaLiKSeSJdIwbLLOvTq2yeSZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:15.150770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.01254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:584c433801f14580c5b0db471eb252f56f7ced1c346d9647b51ccb00d510e979","sha256:ae44127fca68e95893c3925039eb1cc91796fdcc2c1011c00db0fb96bccd2880"],"state_sha256":"fa9d80bdbecc33917d6ba62fd48068d5f6fc9814aea32595e42b2c4cf5c776b8"}