{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SMSLW3Y6YQAX2334SKTLNHU62T","short_pith_number":"pith:SMSLW3Y6","schema_version":"1.0","canonical_sha256":"9324bb6f1ec4017d6f7c92a6b69e9ed4e185c2d5bed96f5be15acebab1158164","source":{"kind":"arxiv","id":"2008.04470","version":1},"attestation_state":"computed","paper":{"title":"PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss","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, Jean-Marc Valin, Karim Helwani, Neerad Phansalkar, Ritwik Giri, Umut Isik","submitted_at":"2020-08-11T01:24:45Z","abstract_excerpt":"Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is encountered in training data. We introduce several innovations that lead to better large neural networks for speech enhancement. The novel PoCoNet architecture is a convolutional neural network that, with the use of frequency-positional embeddings, is able to more efficiently build frequency-dependent features in the early layers. A semi-supervised method helps increa"},"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":"2008.04470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T01:24:45Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SD","stat.ML"],"title_canon_sha256":"e6bb92a2503cdbdcd2fe84f7d31c1960920c166d340e63292d2ca29d07ce6125","abstract_canon_sha256":"865fc5ed2187567934bd472c83ad5a40142125b6086375424358fb95d108f25c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:25.277106Z","signature_b64":"xO6LN+hEUGXYZI6QZbr8tNCF9Iyj/8SQdUDvyA4AXPHtYaUaeQOKjV5DqaLtK/rXEXcNg62cBbu5hgtfxjOdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9324bb6f1ec4017d6f7c92a6b69e9ed4e185c2d5bed96f5be15acebab1158164","last_reissued_at":"2026-07-05T01:26:25.276698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:25.276698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss","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, Jean-Marc Valin, Karim Helwani, Neerad Phansalkar, Ritwik Giri, Umut Isik","submitted_at":"2020-08-11T01:24:45Z","abstract_excerpt":"Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is encountered in training data. We introduce several innovations that lead to better large neural networks for speech enhancement. The novel PoCoNet architecture is a convolutional neural network that, with the use of frequency-positional embeddings, is able to more efficiently build frequency-dependent features in the early layers. A semi-supervised method helps increa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04470","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/2008.04470/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":"2008.04470","created_at":"2026-07-05T01:26:25.276766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.04470v1","created_at":"2026-07-05T01:26:25.276766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04470","created_at":"2026-07-05T01:26:25.276766+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMSLW3Y6YQAX","created_at":"2026-07-05T01:26:25.276766+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMSLW3Y6YQAX2334","created_at":"2026-07-05T01:26:25.276766+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMSLW3Y6","created_at":"2026-07-05T01:26:25.276766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06098","citing_title":"An adaptive filter bank based neural network approach for time delay estimation and speech enhancement","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T","json":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T.json","graph_json":"https://pith.science/api/pith-number/SMSLW3Y6YQAX2334SKTLNHU62T/graph.json","events_json":"https://pith.science/api/pith-number/SMSLW3Y6YQAX2334SKTLNHU62T/events.json","paper":"https://pith.science/paper/SMSLW3Y6"},"agent_actions":{"view_html":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T","download_json":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T.json","view_paper":"https://pith.science/paper/SMSLW3Y6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.04470&json=true","fetch_graph":"https://pith.science/api/pith-number/SMSLW3Y6YQAX2334SKTLNHU62T/graph.json","fetch_events":"https://pith.science/api/pith-number/SMSLW3Y6YQAX2334SKTLNHU62T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T/action/storage_attestation","attest_author":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T/action/author_attestation","sign_citation":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T/action/citation_signature","submit_replication":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T/action/replication_record"}},"created_at":"2026-07-05T01:26:25.276766+00:00","updated_at":"2026-07-05T01:26:25.276766+00:00"}