{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BENUCBQXFIABRFU3FT4LTL5VVI","short_pith_number":"pith:BENUCBQX","schema_version":"1.0","canonical_sha256":"091b4106172a0018969b2cf8b9afb5aa3e30714b20ce0f34446c6bc7ef3d57ea","source":{"kind":"arxiv","id":"2002.09286","version":1},"attestation_state":"computed","paper":{"title":"Efficient Trainable Front-Ends for Neural Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Arvindh Krishnaswamy, Jonah Casebeer, Shrikant Venkataramani, Umut Isik","submitted_at":"2020-02-20T01:51:15Z","abstract_excerpt":"Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literature, these are implemented as large Discrete Fourier Transform matrices; which are prohibitively inefficient for low-compute systems. We present an efficient, trainable front-end based on the butterfly mechanism to compute the Fast Fourier Transform, and show its accuracy and efficiency benefits for low-compute neural speech enhancement models. We also explore the effects of mak"},"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":"2002.09286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-20T01:51:15Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SD","stat.ML"],"title_canon_sha256":"56367ca666ab4d4ff4128a0adf06df8671ba4f9e7d7b92930e029a585190a4db","abstract_canon_sha256":"bee30ceea3880765c1682b52be7f3daccc383200375d71b03d202a262f89d8ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:54.771992Z","signature_b64":"q1v3hWh3baAt7aw5Jxy95YV70VN8GvRXm0HXaQPg1rz/ylPp9Ou826oRDAQ5qOytOSLnYkOSiWrOGCVH4VhmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"091b4106172a0018969b2cf8b9afb5aa3e30714b20ce0f34446c6bc7ef3d57ea","last_reissued_at":"2026-07-05T00:42:54.771606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:54.771606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Trainable Front-Ends for Neural Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Arvindh Krishnaswamy, Jonah Casebeer, Shrikant Venkataramani, Umut Isik","submitted_at":"2020-02-20T01:51:15Z","abstract_excerpt":"Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literature, these are implemented as large Discrete Fourier Transform matrices; which are prohibitively inefficient for low-compute systems. We present an efficient, trainable front-end based on the butterfly mechanism to compute the Fast Fourier Transform, and show its accuracy and efficiency benefits for low-compute neural speech enhancement models. We also explore the effects of mak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09286","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.09286/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":"2002.09286","created_at":"2026-07-05T00:42:54.771665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09286v1","created_at":"2026-07-05T00:42:54.771665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09286","created_at":"2026-07-05T00:42:54.771665+00:00"},{"alias_kind":"pith_short_12","alias_value":"BENUCBQXFIAB","created_at":"2026-07-05T00:42:54.771665+00:00"},{"alias_kind":"pith_short_16","alias_value":"BENUCBQXFIABRFU3","created_at":"2026-07-05T00:42:54.771665+00:00"},{"alias_kind":"pith_short_8","alias_value":"BENUCBQX","created_at":"2026-07-05T00:42:54.771665+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/BENUCBQXFIABRFU3FT4LTL5VVI","json":"https://pith.science/pith/BENUCBQXFIABRFU3FT4LTL5VVI.json","graph_json":"https://pith.science/api/pith-number/BENUCBQXFIABRFU3FT4LTL5VVI/graph.json","events_json":"https://pith.science/api/pith-number/BENUCBQXFIABRFU3FT4LTL5VVI/events.json","paper":"https://pith.science/paper/BENUCBQX"},"agent_actions":{"view_html":"https://pith.science/pith/BENUCBQXFIABRFU3FT4LTL5VVI","download_json":"https://pith.science/pith/BENUCBQXFIABRFU3FT4LTL5VVI.json","view_paper":"https://pith.science/paper/BENUCBQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09286&json=true","fetch_graph":"https://pith.science/api/pith-number/BENUCBQXFIABRFU3FT4LTL5VVI/graph.json","fetch_events":"https://pith.science/api/pith-number/BENUCBQXFIABRFU3FT4LTL5VVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BENUCBQXFIABRFU3FT4LTL5VVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BENUCBQXFIABRFU3FT4LTL5VVI/action/storage_attestation","attest_author":"https://pith.science/pith/BENUCBQXFIABRFU3FT4LTL5VVI/action/author_attestation","sign_citation":"https://pith.science/pith/BENUCBQXFIABRFU3FT4LTL5VVI/action/citation_signature","submit_replication":"https://pith.science/pith/BENUCBQXFIABRFU3FT4LTL5VVI/action/replication_record"}},"created_at":"2026-07-05T00:42:54.771665+00:00","updated_at":"2026-07-05T00:42:54.771665+00:00"}