{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4CKK5KQE7BGGMPQ6N6NHUSVUPK","short_pith_number":"pith:4CKK5KQE","schema_version":"1.0","canonical_sha256":"e094aeaa04f84c663e1e6f9a7a4ab47ab27b23615bc59358dd7c2e3b9902b683","source":{"kind":"arxiv","id":"1711.10282","version":2},"attestation_state":"computed","paper":{"title":"Learning from Between-class Examples for Deep Sound Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tatsuya Harada, Yoshitaka Ushiku, Yuji Tokozume","submitted_at":"2017-11-28T13:29:45Z","abstract_excerpt":"Deep learning methods have achieved high performance in sound recognition tasks. Deciding how to feed the training data is important for further performance improvement. We propose a novel learning method for deep sound recognition: Between-Class learning (BC learning). Our strategy is to learn a discriminative feature space by recognizing the between-class sounds as between-class sounds. We generate between-class sounds by mixing two sounds belonging to different classes with a random ratio. We then input the mixed sound to the model and train the model to output the mixing ratio. The advanta"},"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":"1711.10282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T13:29:45Z","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"cfd2f5538fbb1970316e28c85bf805bfe5ecf977732f3f72275640e9cc378bd6","abstract_canon_sha256":"d4a256e83815c60f6d93ca2b3190c8d5f79fb4690483eab61ec68a70cc38c856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:18.476787Z","signature_b64":"Lp2qcMgyoGN0AtXh3bMk/ErpH+MraCctIq9bzg9XE0S5L109DTQ++zV4Kfq7F2V274zVg4LKcqDX/f38lpoADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e094aeaa04f84c663e1e6f9a7a4ab47ab27b23615bc59358dd7c2e3b9902b683","last_reissued_at":"2026-05-18T00:22:18.476185Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:18.476185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Between-class Examples for Deep Sound Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tatsuya Harada, Yoshitaka Ushiku, Yuji Tokozume","submitted_at":"2017-11-28T13:29:45Z","abstract_excerpt":"Deep learning methods have achieved high performance in sound recognition tasks. Deciding how to feed the training data is important for further performance improvement. We propose a novel learning method for deep sound recognition: Between-Class learning (BC learning). Our strategy is to learn a discriminative feature space by recognizing the between-class sounds as between-class sounds. We generate between-class sounds by mixing two sounds belonging to different classes with a random ratio. We then input the mixed sound to the model and train the model to output the mixing ratio. The advanta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10282","kind":"arxiv","version":2},"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":"1711.10282","created_at":"2026-05-18T00:22:18.476275+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.10282v2","created_at":"2026-05-18T00:22:18.476275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10282","created_at":"2026-05-18T00:22:18.476275+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CKK5KQE7BGG","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CKK5KQE7BGGMPQ6","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CKK5KQE","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.02230","citing_title":"Attention based Convolutional Recurrent Neural Network for Environmental Sound Classification","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2411.16121","citing_title":"DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09716","citing_title":"Medical Model Synthesis Architectures: A Case Study","ref_index":179,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CKK5KQE7BGGMPQ6N6NHUSVUPK","json":"https://pith.science/pith/4CKK5KQE7BGGMPQ6N6NHUSVUPK.json","graph_json":"https://pith.science/api/pith-number/4CKK5KQE7BGGMPQ6N6NHUSVUPK/graph.json","events_json":"https://pith.science/api/pith-number/4CKK5KQE7BGGMPQ6N6NHUSVUPK/events.json","paper":"https://pith.science/paper/4CKK5KQE"},"agent_actions":{"view_html":"https://pith.science/pith/4CKK5KQE7BGGMPQ6N6NHUSVUPK","download_json":"https://pith.science/pith/4CKK5KQE7BGGMPQ6N6NHUSVUPK.json","view_paper":"https://pith.science/paper/4CKK5KQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.10282&json=true","fetch_graph":"https://pith.science/api/pith-number/4CKK5KQE7BGGMPQ6N6NHUSVUPK/graph.json","fetch_events":"https://pith.science/api/pith-number/4CKK5KQE7BGGMPQ6N6NHUSVUPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CKK5KQE7BGGMPQ6N6NHUSVUPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CKK5KQE7BGGMPQ6N6NHUSVUPK/action/storage_attestation","attest_author":"https://pith.science/pith/4CKK5KQE7BGGMPQ6N6NHUSVUPK/action/author_attestation","sign_citation":"https://pith.science/pith/4CKK5KQE7BGGMPQ6N6NHUSVUPK/action/citation_signature","submit_replication":"https://pith.science/pith/4CKK5KQE7BGGMPQ6N6NHUSVUPK/action/replication_record"}},"created_at":"2026-05-18T00:22:18.476275+00:00","updated_at":"2026-05-18T00:22:18.476275+00:00"}