{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JFYNSVQNVABMBJYUHOMJTNCEVP","short_pith_number":"pith:JFYNSVQN","schema_version":"1.0","canonical_sha256":"4970d9560da802c0a7143b9899b444abfeefacc3d61b8a001fb0255575cfdc1d","source":{"kind":"arxiv","id":"1803.10219","version":1},"attestation_state":"computed","paper":{"title":"Learning Environmental Sounds with Multi-scale Convolutional Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Boqing Zhu, Changjian Wang, Feng Liu, Jin Lei, Yuxing Peng, Zengquan Lu","submitted_at":"2018-03-25T04:46:17Z","abstract_excerpt":"Deep learning has dramatically improved the performance of sounds recognition. However, learning acoustic models directly from the raw waveform is still challenging. Current waveform-based models generally use time-domain convolutional layers to extract features. The features extracted by single size filters are insufficient for building discriminative representation of audios. In this paper, we propose multi-scale convolution operation, which can get better audio representation by improving the frequency resolution and learning filters cross all frequency area. For leveraging the waveform-bas"},"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":"1803.10219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-03-25T04:46:17Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5a403fd61215881e98fbda68db6831149fec0f1695f3ea91f8fb373524e84e34","abstract_canon_sha256":"8c8030119f4c9ded8992a5e574a86b150fc7dd17d66efae0cac50a7e0f44d7b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:56.091876Z","signature_b64":"jFMHfSGBxg9EPYzJlKvUINjDQmgRN3ajPhOpyB2kEuoZJILkhN/iEyCr7l62IWGYCYYQo2PIJdJZvJwk82K1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4970d9560da802c0a7143b9899b444abfeefacc3d61b8a001fb0255575cfdc1d","last_reissued_at":"2026-05-18T00:19:56.091084Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:56.091084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Environmental Sounds with Multi-scale Convolutional Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Boqing Zhu, Changjian Wang, Feng Liu, Jin Lei, Yuxing Peng, Zengquan Lu","submitted_at":"2018-03-25T04:46:17Z","abstract_excerpt":"Deep learning has dramatically improved the performance of sounds recognition. However, learning acoustic models directly from the raw waveform is still challenging. Current waveform-based models generally use time-domain convolutional layers to extract features. The features extracted by single size filters are insufficient for building discriminative representation of audios. In this paper, we propose multi-scale convolution operation, which can get better audio representation by improving the frequency resolution and learning filters cross all frequency area. For leveraging the waveform-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10219","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":"1803.10219","created_at":"2026-05-18T00:19:56.091187+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10219v1","created_at":"2026-05-18T00:19:56.091187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10219","created_at":"2026-05-18T00:19:56.091187+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFYNSVQNVABM","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFYNSVQNVABMBJYU","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFYNSVQN","created_at":"2026-05-18T12:32:31.084164+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":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFYNSVQNVABMBJYUHOMJTNCEVP","json":"https://pith.science/pith/JFYNSVQNVABMBJYUHOMJTNCEVP.json","graph_json":"https://pith.science/api/pith-number/JFYNSVQNVABMBJYUHOMJTNCEVP/graph.json","events_json":"https://pith.science/api/pith-number/JFYNSVQNVABMBJYUHOMJTNCEVP/events.json","paper":"https://pith.science/paper/JFYNSVQN"},"agent_actions":{"view_html":"https://pith.science/pith/JFYNSVQNVABMBJYUHOMJTNCEVP","download_json":"https://pith.science/pith/JFYNSVQNVABMBJYUHOMJTNCEVP.json","view_paper":"https://pith.science/paper/JFYNSVQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10219&json=true","fetch_graph":"https://pith.science/api/pith-number/JFYNSVQNVABMBJYUHOMJTNCEVP/graph.json","fetch_events":"https://pith.science/api/pith-number/JFYNSVQNVABMBJYUHOMJTNCEVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFYNSVQNVABMBJYUHOMJTNCEVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFYNSVQNVABMBJYUHOMJTNCEVP/action/storage_attestation","attest_author":"https://pith.science/pith/JFYNSVQNVABMBJYUHOMJTNCEVP/action/author_attestation","sign_citation":"https://pith.science/pith/JFYNSVQNVABMBJYUHOMJTNCEVP/action/citation_signature","submit_replication":"https://pith.science/pith/JFYNSVQNVABMBJYUHOMJTNCEVP/action/replication_record"}},"created_at":"2026-05-18T00:19:56.091187+00:00","updated_at":"2026-05-18T00:19:56.091187+00:00"}