{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OPLHYZXEVDU2MIR6ZFBBTRXHUG","short_pith_number":"pith:OPLHYZXE","schema_version":"1.0","canonical_sha256":"73d67c66e4a8e9a6223ec94219c6e7a1be075ffcfcfb1c93b32e025e739c96a4","source":{"kind":"arxiv","id":"1901.08608","version":1},"attestation_state":"computed","paper":{"title":"Multi-stream Network With Temporal Attention For Environmental Sound Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Katrin Kirchhoff, Venkata Chebiyyam, Xinyu Li","submitted_at":"2019-01-24T19:02:17Z","abstract_excerpt":"Environmental sound classification systems often do not perform robustly across different sound classification tasks and audio signals of varying temporal structures. We introduce a multi-stream convolutional neural network with temporal attention that addresses these problems. The network relies on three input streams consisting of raw audio and spectral features and utilizes a temporal attention function computed from energy changes over time. Training and classification utilizes decision fusion and data augmentation techniques that incorporate uncertainty. We evaluate this network on three "},"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":"1901.08608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-01-24T19:02:17Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"a34f64e6f10c26ca4070933b87fdfac04322af9db0949087520b88a027e3d67b","abstract_canon_sha256":"fd63e868be49bddb36711abeb55f2be5e795bc03b2dece1cd170054aa3702e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:33.605393Z","signature_b64":"ie9QLARvAoCM2jiXcxXvr/8020ZA/o+1v/g4GShuQKzy3BI/qEDZz1KKQgOSotSyVJ/LWaa88OcHJdc17qpsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73d67c66e4a8e9a6223ec94219c6e7a1be075ffcfcfb1c93b32e025e739c96a4","last_reissued_at":"2026-05-17T23:55:33.604952Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:33.604952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-stream Network With Temporal Attention For Environmental Sound Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Katrin Kirchhoff, Venkata Chebiyyam, Xinyu Li","submitted_at":"2019-01-24T19:02:17Z","abstract_excerpt":"Environmental sound classification systems often do not perform robustly across different sound classification tasks and audio signals of varying temporal structures. We introduce a multi-stream convolutional neural network with temporal attention that addresses these problems. The network relies on three input streams consisting of raw audio and spectral features and utilizes a temporal attention function computed from energy changes over time. Training and classification utilizes decision fusion and data augmentation techniques that incorporate uncertainty. We evaluate this network on three "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08608","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":"1901.08608","created_at":"2026-05-17T23:55:33.605033+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08608v1","created_at":"2026-05-17T23:55:33.605033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08608","created_at":"2026-05-17T23:55:33.605033+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPLHYZXEVDU2","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPLHYZXEVDU2MIR6","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPLHYZXE","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02230","citing_title":"Attention based Convolutional Recurrent Neural Network for Environmental Sound Classification","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPLHYZXEVDU2MIR6ZFBBTRXHUG","json":"https://pith.science/pith/OPLHYZXEVDU2MIR6ZFBBTRXHUG.json","graph_json":"https://pith.science/api/pith-number/OPLHYZXEVDU2MIR6ZFBBTRXHUG/graph.json","events_json":"https://pith.science/api/pith-number/OPLHYZXEVDU2MIR6ZFBBTRXHUG/events.json","paper":"https://pith.science/paper/OPLHYZXE"},"agent_actions":{"view_html":"https://pith.science/pith/OPLHYZXEVDU2MIR6ZFBBTRXHUG","download_json":"https://pith.science/pith/OPLHYZXEVDU2MIR6ZFBBTRXHUG.json","view_paper":"https://pith.science/paper/OPLHYZXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08608&json=true","fetch_graph":"https://pith.science/api/pith-number/OPLHYZXEVDU2MIR6ZFBBTRXHUG/graph.json","fetch_events":"https://pith.science/api/pith-number/OPLHYZXEVDU2MIR6ZFBBTRXHUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPLHYZXEVDU2MIR6ZFBBTRXHUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPLHYZXEVDU2MIR6ZFBBTRXHUG/action/storage_attestation","attest_author":"https://pith.science/pith/OPLHYZXEVDU2MIR6ZFBBTRXHUG/action/author_attestation","sign_citation":"https://pith.science/pith/OPLHYZXEVDU2MIR6ZFBBTRXHUG/action/citation_signature","submit_replication":"https://pith.science/pith/OPLHYZXEVDU2MIR6ZFBBTRXHUG/action/replication_record"}},"created_at":"2026-05-17T23:55:33.605033+00:00","updated_at":"2026-05-17T23:55:33.605033+00:00"}