{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SY37Y2PMXIEHKXDGTPTOMIHDT4","short_pith_number":"pith:SY37Y2PM","schema_version":"1.0","canonical_sha256":"9637fc69ecba08755c669be6e620e39f152cede48fadf473c7d09e094f4fe166","source":{"kind":"arxiv","id":"2208.11460","version":3},"attestation_state":"computed","paper":{"title":"Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Gerhard Widmer, Paul Primus","submitted_at":"2022-08-24T11:54:42Z","abstract_excerpt":"The absence of large labeled datasets remains a significant challenge in many application areas of deep learning. Researchers and practitioners typically resort to transfer learning and data augmentation to alleviate this issue. We study these strategies in the context of audio retrieval with natural language queries (Task 6b of the DCASE 2022 Challenge). Our proposed system uses pre-trained embedding models to project recordings and textual descriptions into a shared audio-caption space in which related examples from different modalities are close. We employ various data augmentation techniqu"},"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":"2208.11460","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-24T11:54:42Z","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"404b61049ceeeb32d93ea4375cd9b6fe6005facd397c7b8d213502b6a339b0b7","abstract_canon_sha256":"867d36f6c6e2dc22a4272833928b42dfe38bb0ea2012a344f889da8998fb3a45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:41.937762Z","signature_b64":"I1S0WNRqk17Ufkykzhi8WJ2/6uZWRIfAWfd2gHQ17Sps7+H4SijKSHkhHyAEfNUTTMhfYyXq31ustVWfk6vlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9637fc69ecba08755c669be6e620e39f152cede48fadf473c7d09e094f4fe166","last_reissued_at":"2026-07-05T05:11:41.937371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:41.937371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Gerhard Widmer, Paul Primus","submitted_at":"2022-08-24T11:54:42Z","abstract_excerpt":"The absence of large labeled datasets remains a significant challenge in many application areas of deep learning. Researchers and practitioners typically resort to transfer learning and data augmentation to alleviate this issue. We study these strategies in the context of audio retrieval with natural language queries (Task 6b of the DCASE 2022 Challenge). Our proposed system uses pre-trained embedding models to project recordings and textual descriptions into a shared audio-caption space in which related examples from different modalities are close. We employ various data augmentation techniqu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11460","kind":"arxiv","version":3},"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/2208.11460/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":"2208.11460","created_at":"2026-07-05T05:11:41.937430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.11460v3","created_at":"2026-07-05T05:11:41.937430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11460","created_at":"2026-07-05T05:11:41.937430+00:00"},{"alias_kind":"pith_short_12","alias_value":"SY37Y2PMXIEH","created_at":"2026-07-05T05:11:41.937430+00:00"},{"alias_kind":"pith_short_16","alias_value":"SY37Y2PMXIEHKXDG","created_at":"2026-07-05T05:11:41.937430+00:00"},{"alias_kind":"pith_short_8","alias_value":"SY37Y2PM","created_at":"2026-07-05T05:11:41.937430+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/SY37Y2PMXIEHKXDGTPTOMIHDT4","json":"https://pith.science/pith/SY37Y2PMXIEHKXDGTPTOMIHDT4.json","graph_json":"https://pith.science/api/pith-number/SY37Y2PMXIEHKXDGTPTOMIHDT4/graph.json","events_json":"https://pith.science/api/pith-number/SY37Y2PMXIEHKXDGTPTOMIHDT4/events.json","paper":"https://pith.science/paper/SY37Y2PM"},"agent_actions":{"view_html":"https://pith.science/pith/SY37Y2PMXIEHKXDGTPTOMIHDT4","download_json":"https://pith.science/pith/SY37Y2PMXIEHKXDGTPTOMIHDT4.json","view_paper":"https://pith.science/paper/SY37Y2PM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.11460&json=true","fetch_graph":"https://pith.science/api/pith-number/SY37Y2PMXIEHKXDGTPTOMIHDT4/graph.json","fetch_events":"https://pith.science/api/pith-number/SY37Y2PMXIEHKXDGTPTOMIHDT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SY37Y2PMXIEHKXDGTPTOMIHDT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SY37Y2PMXIEHKXDGTPTOMIHDT4/action/storage_attestation","attest_author":"https://pith.science/pith/SY37Y2PMXIEHKXDGTPTOMIHDT4/action/author_attestation","sign_citation":"https://pith.science/pith/SY37Y2PMXIEHKXDGTPTOMIHDT4/action/citation_signature","submit_replication":"https://pith.science/pith/SY37Y2PMXIEHKXDGTPTOMIHDT4/action/replication_record"}},"created_at":"2026-07-05T05:11:41.937430+00:00","updated_at":"2026-07-05T05:11:41.937430+00:00"}