{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OO5GTTD2OIQ5JB2OJLU66P7BDV","short_pith_number":"pith:OO5GTTD2","schema_version":"1.0","canonical_sha256":"73ba69cc7a7221d4874e4ae9ef3fe11d53c8d1c750f6db4a21f222563e7640c6","source":{"kind":"arxiv","id":"1709.07124","version":1},"attestation_state":"computed","paper":{"title":"Deep Recurrent NMF for Speech Separation by Unfolding Iterative Thresholding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.SD","authors_text":"James Pitton, Les Atlas, Scott Wisdom, Thomas Powers","submitted_at":"2017-09-21T01:46:19Z","abstract_excerpt":"In this paper, we propose a novel recurrent neural network architecture for speech separation. This architecture is constructed by unfolding the iterations of a sequential iterative soft-thresholding algorithm (ISTA) that solves the optimization problem for sparse nonnegative matrix factorization (NMF) of spectrograms. We name this network architecture deep recurrent NMF (DR-NMF). The proposed DR-NMF network has three distinct advantages. First, DR-NMF provides better interpretability than other deep architectures, since the weights correspond to NMF model parameters, even after training. This"},"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":"1709.07124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-09-21T01:46:19Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"24cc9f388829970a52430a6d00a23a68a9c8ad92e80066280517b13c416a139f","abstract_canon_sha256":"d3e542ea3becf94002fdced74b0d96dee871127829717983f33e80102f674f74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:36.526945Z","signature_b64":"zFQRpu0pmBI6+JVkWbX8jkBds1QtF+38KR5cKwYKokHkSxWONxMkhicYwSKwAiFppalUFOI7FWgBhiSefnoQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73ba69cc7a7221d4874e4ae9ef3fe11d53c8d1c750f6db4a21f222563e7640c6","last_reissued_at":"2026-05-18T00:34:36.526486Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:36.526486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Recurrent NMF for Speech Separation by Unfolding Iterative Thresholding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.SD","authors_text":"James Pitton, Les Atlas, Scott Wisdom, Thomas Powers","submitted_at":"2017-09-21T01:46:19Z","abstract_excerpt":"In this paper, we propose a novel recurrent neural network architecture for speech separation. This architecture is constructed by unfolding the iterations of a sequential iterative soft-thresholding algorithm (ISTA) that solves the optimization problem for sparse nonnegative matrix factorization (NMF) of spectrograms. We name this network architecture deep recurrent NMF (DR-NMF). The proposed DR-NMF network has three distinct advantages. First, DR-NMF provides better interpretability than other deep architectures, since the weights correspond to NMF model parameters, even after training. This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.07124","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":""},"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":"1709.07124","created_at":"2026-05-18T00:34:36.526560+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.07124v1","created_at":"2026-05-18T00:34:36.526560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.07124","created_at":"2026-05-18T00:34:36.526560+00:00"},{"alias_kind":"pith_short_12","alias_value":"OO5GTTD2OIQ5","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OO5GTTD2OIQ5JB2O","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OO5GTTD2","created_at":"2026-05-18T12:31:34.259226+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/OO5GTTD2OIQ5JB2OJLU66P7BDV","json":"https://pith.science/pith/OO5GTTD2OIQ5JB2OJLU66P7BDV.json","graph_json":"https://pith.science/api/pith-number/OO5GTTD2OIQ5JB2OJLU66P7BDV/graph.json","events_json":"https://pith.science/api/pith-number/OO5GTTD2OIQ5JB2OJLU66P7BDV/events.json","paper":"https://pith.science/paper/OO5GTTD2"},"agent_actions":{"view_html":"https://pith.science/pith/OO5GTTD2OIQ5JB2OJLU66P7BDV","download_json":"https://pith.science/pith/OO5GTTD2OIQ5JB2OJLU66P7BDV.json","view_paper":"https://pith.science/paper/OO5GTTD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.07124&json=true","fetch_graph":"https://pith.science/api/pith-number/OO5GTTD2OIQ5JB2OJLU66P7BDV/graph.json","fetch_events":"https://pith.science/api/pith-number/OO5GTTD2OIQ5JB2OJLU66P7BDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OO5GTTD2OIQ5JB2OJLU66P7BDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OO5GTTD2OIQ5JB2OJLU66P7BDV/action/storage_attestation","attest_author":"https://pith.science/pith/OO5GTTD2OIQ5JB2OJLU66P7BDV/action/author_attestation","sign_citation":"https://pith.science/pith/OO5GTTD2OIQ5JB2OJLU66P7BDV/action/citation_signature","submit_replication":"https://pith.science/pith/OO5GTTD2OIQ5JB2OJLU66P7BDV/action/replication_record"}},"created_at":"2026-05-18T00:34:36.526560+00:00","updated_at":"2026-05-18T00:34:36.526560+00:00"}