{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OXDSPRLNPLH7QOWONSPB7SY6QU","short_pith_number":"pith:OXDSPRLN","schema_version":"1.0","canonical_sha256":"75c727c56d7acff83ace6c9e1fcb1e8522c2fb88f8b32e2de6438d51acff2b04","source":{"kind":"arxiv","id":"2211.01751","version":4},"attestation_state":"computed","paper":{"title":"Iterative autoregression: a novel trick to improve your low-latency speech enhancement model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aibek Alanov, Azat Saginbaev, Ivan Shchekotov, Nicholas Babaev, Pavel Andreev","submitted_at":"2022-11-03T12:32:33Z","abstract_excerpt":"Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is generally considered a challenging task and has a significant negative impact on the model's quality. However, the sequential nature of streaming generation offers a natural possibility for autoregression, that is, utilizing previous predictions while making current ones. The conventional method for training autoregressive models is teacher forcing, but its p"},"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":"2211.01751","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-03T12:32:33Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"aaa99971c1f47125b41532e94c2990cb67394dfebbd141b33867b3775f38e3d5","abstract_canon_sha256":"d40989db90f37be97129bfb30de3f52b97a45411b081615f666163645d23974b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:06.335145Z","signature_b64":"61rVAEXuY0YQ9GQiHUQNq56/tLOU02MRvjsLDqlBuT9G3u+Nv4WftsqfzKxXhIOmeyb7WJ5D+pXVa/vACPJdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75c727c56d7acff83ace6c9e1fcb1e8522c2fb88f8b32e2de6438d51acff2b04","last_reissued_at":"2026-07-05T07:20:06.334536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:06.334536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterative autoregression: a novel trick to improve your low-latency speech enhancement model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aibek Alanov, Azat Saginbaev, Ivan Shchekotov, Nicholas Babaev, Pavel Andreev","submitted_at":"2022-11-03T12:32:33Z","abstract_excerpt":"Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is generally considered a challenging task and has a significant negative impact on the model's quality. However, the sequential nature of streaming generation offers a natural possibility for autoregression, that is, utilizing previous predictions while making current ones. The conventional method for training autoregressive models is teacher forcing, but its p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01751","kind":"arxiv","version":4},"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/2211.01751/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":"2211.01751","created_at":"2026-07-05T07:20:06.334595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01751v4","created_at":"2026-07-05T07:20:06.334595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01751","created_at":"2026-07-05T07:20:06.334595+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXDSPRLNPLH7","created_at":"2026-07-05T07:20:06.334595+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXDSPRLNPLH7QOWO","created_at":"2026-07-05T07:20:06.334595+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXDSPRLN","created_at":"2026-07-05T07:20:06.334595+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/OXDSPRLNPLH7QOWONSPB7SY6QU","json":"https://pith.science/pith/OXDSPRLNPLH7QOWONSPB7SY6QU.json","graph_json":"https://pith.science/api/pith-number/OXDSPRLNPLH7QOWONSPB7SY6QU/graph.json","events_json":"https://pith.science/api/pith-number/OXDSPRLNPLH7QOWONSPB7SY6QU/events.json","paper":"https://pith.science/paper/OXDSPRLN"},"agent_actions":{"view_html":"https://pith.science/pith/OXDSPRLNPLH7QOWONSPB7SY6QU","download_json":"https://pith.science/pith/OXDSPRLNPLH7QOWONSPB7SY6QU.json","view_paper":"https://pith.science/paper/OXDSPRLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01751&json=true","fetch_graph":"https://pith.science/api/pith-number/OXDSPRLNPLH7QOWONSPB7SY6QU/graph.json","fetch_events":"https://pith.science/api/pith-number/OXDSPRLNPLH7QOWONSPB7SY6QU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXDSPRLNPLH7QOWONSPB7SY6QU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXDSPRLNPLH7QOWONSPB7SY6QU/action/storage_attestation","attest_author":"https://pith.science/pith/OXDSPRLNPLH7QOWONSPB7SY6QU/action/author_attestation","sign_citation":"https://pith.science/pith/OXDSPRLNPLH7QOWONSPB7SY6QU/action/citation_signature","submit_replication":"https://pith.science/pith/OXDSPRLNPLH7QOWONSPB7SY6QU/action/replication_record"}},"created_at":"2026-07-05T07:20:06.334595+00:00","updated_at":"2026-07-05T07:20:06.334595+00:00"}