{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7IXOIMH7HUBJWM3QCK6GB3FJZ4","short_pith_number":"pith:7IXOIMH7","schema_version":"1.0","canonical_sha256":"fa2ee430ff3d029b337012bc60eca9cf1572ff55ef3a84e6e67f5c6c6007c858","source":{"kind":"arxiv","id":"2409.18239","version":2},"attestation_state":"computed","paper":{"title":"Towards Sub-millisecond Latency Real-Time Speech Enhancement Models on Hearables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Artem Dementyev, Chandan K. A. Reddy, John R. Hershey, Navin Chatlani, Richard F.Lyon, Scott Wisdom","submitted_at":"2024-09-26T19:31:05Z","abstract_excerpt":"Low latency models are critical for real-time speech enhancement applications, such as hearing aids and hearables. However, the sub-millisecond latency space for resource-constrained hearables remains underexplored. We demonstrate speech enhancement using a computationally efficient minimum-phase FIR filter, enabling sample-by-sample processing to achieve mean algorithmic latency of 0.32 ms to 1.25 ms. With a single microphone, we observe a mean SI-SDRi of 4.1 dB. The approach shows generalization with a DNSMOS increase of 0.2 on unseen audio recordings. We use a lightweight LSTM-based model o"},"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":"2409.18239","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-26T19:31:05Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"fa8bf143f0fc21fee3d7b311b78ea7b1fdbe44522e742c89908b64365bff66a7","abstract_canon_sha256":"091443f30760aaf2e487e510d50a1fcd6c2546e692b9fdb7ba3f66f6109bda4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:40.100547Z","signature_b64":"aLgsMboxPhnSwL0OCvX4CivmiZiaenlYh1Ec9Nmrc0MSQSysWJS0e72gMmqSQW5aGSbCWMXtapTVryX9bEjaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa2ee430ff3d029b337012bc60eca9cf1572ff55ef3a84e6e67f5c6c6007c858","last_reissued_at":"2026-07-05T10:26:40.098668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:40.098668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Sub-millisecond Latency Real-Time Speech Enhancement Models on Hearables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Artem Dementyev, Chandan K. A. Reddy, John R. Hershey, Navin Chatlani, Richard F.Lyon, Scott Wisdom","submitted_at":"2024-09-26T19:31:05Z","abstract_excerpt":"Low latency models are critical for real-time speech enhancement applications, such as hearing aids and hearables. However, the sub-millisecond latency space for resource-constrained hearables remains underexplored. We demonstrate speech enhancement using a computationally efficient minimum-phase FIR filter, enabling sample-by-sample processing to achieve mean algorithmic latency of 0.32 ms to 1.25 ms. With a single microphone, we observe a mean SI-SDRi of 4.1 dB. The approach shows generalization with a DNSMOS increase of 0.2 on unseen audio recordings. We use a lightweight LSTM-based model o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18239","kind":"arxiv","version":2},"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/2409.18239/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":"2409.18239","created_at":"2026-07-05T10:26:40.098822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18239v2","created_at":"2026-07-05T10:26:40.098822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18239","created_at":"2026-07-05T10:26:40.098822+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IXOIMH7HUBJ","created_at":"2026-07-05T10:26:40.098822+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IXOIMH7HUBJWM3Q","created_at":"2026-07-05T10:26:40.098822+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IXOIMH7","created_at":"2026-07-05T10:26:40.098822+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/7IXOIMH7HUBJWM3QCK6GB3FJZ4","json":"https://pith.science/pith/7IXOIMH7HUBJWM3QCK6GB3FJZ4.json","graph_json":"https://pith.science/api/pith-number/7IXOIMH7HUBJWM3QCK6GB3FJZ4/graph.json","events_json":"https://pith.science/api/pith-number/7IXOIMH7HUBJWM3QCK6GB3FJZ4/events.json","paper":"https://pith.science/paper/7IXOIMH7"},"agent_actions":{"view_html":"https://pith.science/pith/7IXOIMH7HUBJWM3QCK6GB3FJZ4","download_json":"https://pith.science/pith/7IXOIMH7HUBJWM3QCK6GB3FJZ4.json","view_paper":"https://pith.science/paper/7IXOIMH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18239&json=true","fetch_graph":"https://pith.science/api/pith-number/7IXOIMH7HUBJWM3QCK6GB3FJZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/7IXOIMH7HUBJWM3QCK6GB3FJZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IXOIMH7HUBJWM3QCK6GB3FJZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IXOIMH7HUBJWM3QCK6GB3FJZ4/action/storage_attestation","attest_author":"https://pith.science/pith/7IXOIMH7HUBJWM3QCK6GB3FJZ4/action/author_attestation","sign_citation":"https://pith.science/pith/7IXOIMH7HUBJWM3QCK6GB3FJZ4/action/citation_signature","submit_replication":"https://pith.science/pith/7IXOIMH7HUBJWM3QCK6GB3FJZ4/action/replication_record"}},"created_at":"2026-07-05T10:26:40.098822+00:00","updated_at":"2026-07-05T10:26:40.098822+00:00"}