{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RQYXOFGLDOBB5VC5W3GK4GVLKK","short_pith_number":"pith:RQYXOFGL","schema_version":"1.0","canonical_sha256":"8c317714cb1b821ed45db6ccae1aab52b646df1fc835c99821fd98b670cb54c0","source":{"kind":"arxiv","id":"2407.14329","version":1},"attestation_state":"computed","paper":{"title":"Efficient Audio Captioning with Encoder-Level Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Mark D. Plumbley, Mengyue Wu, Wenwu Wang, Xuenan Xu","submitted_at":"2024-07-19T14:09:50Z","abstract_excerpt":"Significant improvement has been achieved in automated audio captioning (AAC) with recent models. However, these models have become increasingly large as their performance is enhanced. In this work, we propose a knowledge distillation (KD) framework for AAC. Our analysis shows that in the encoder-decoder based AAC models, it is more effective to distill knowledge into the encoder as compared with the decoder. To this end, we incorporate encoder-level KD loss into training, in addition to the standard supervised loss and sequence-level KD loss. We investigate two encoder-level KD methods, based"},"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":"2407.14329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-19T14:09:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3a70aa0e61df0530a0df029d7524c6642b95acc98decceb82949014c1cefe012","abstract_canon_sha256":"e5237b499f898121a13f25c94fcb77a444540bdfb18f47f1e1f77a28a22d60a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:10.803965Z","signature_b64":"3TFKDyLR0XDpC8QJlVDxmDVtXghpv5+8PQSO1s1vQI1F6dcRvXKsR4bv38KZsGrNde8h+lA/GVkeYN5N0jhzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c317714cb1b821ed45db6ccae1aab52b646df1fc835c99821fd98b670cb54c0","last_reissued_at":"2026-07-05T08:46:10.803479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:10.803479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Audio Captioning with Encoder-Level Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Mark D. Plumbley, Mengyue Wu, Wenwu Wang, Xuenan Xu","submitted_at":"2024-07-19T14:09:50Z","abstract_excerpt":"Significant improvement has been achieved in automated audio captioning (AAC) with recent models. However, these models have become increasingly large as their performance is enhanced. In this work, we propose a knowledge distillation (KD) framework for AAC. Our analysis shows that in the encoder-decoder based AAC models, it is more effective to distill knowledge into the encoder as compared with the decoder. To this end, we incorporate encoder-level KD loss into training, in addition to the standard supervised loss and sequence-level KD loss. We investigate two encoder-level KD methods, based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14329","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/2407.14329/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":"2407.14329","created_at":"2026-07-05T08:46:10.803537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14329v1","created_at":"2026-07-05T08:46:10.803537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14329","created_at":"2026-07-05T08:46:10.803537+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQYXOFGLDOBB","created_at":"2026-07-05T08:46:10.803537+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQYXOFGLDOBB5VC5","created_at":"2026-07-05T08:46:10.803537+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQYXOFGL","created_at":"2026-07-05T08:46:10.803537+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/RQYXOFGLDOBB5VC5W3GK4GVLKK","json":"https://pith.science/pith/RQYXOFGLDOBB5VC5W3GK4GVLKK.json","graph_json":"https://pith.science/api/pith-number/RQYXOFGLDOBB5VC5W3GK4GVLKK/graph.json","events_json":"https://pith.science/api/pith-number/RQYXOFGLDOBB5VC5W3GK4GVLKK/events.json","paper":"https://pith.science/paper/RQYXOFGL"},"agent_actions":{"view_html":"https://pith.science/pith/RQYXOFGLDOBB5VC5W3GK4GVLKK","download_json":"https://pith.science/pith/RQYXOFGLDOBB5VC5W3GK4GVLKK.json","view_paper":"https://pith.science/paper/RQYXOFGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14329&json=true","fetch_graph":"https://pith.science/api/pith-number/RQYXOFGLDOBB5VC5W3GK4GVLKK/graph.json","fetch_events":"https://pith.science/api/pith-number/RQYXOFGLDOBB5VC5W3GK4GVLKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQYXOFGLDOBB5VC5W3GK4GVLKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQYXOFGLDOBB5VC5W3GK4GVLKK/action/storage_attestation","attest_author":"https://pith.science/pith/RQYXOFGLDOBB5VC5W3GK4GVLKK/action/author_attestation","sign_citation":"https://pith.science/pith/RQYXOFGLDOBB5VC5W3GK4GVLKK/action/citation_signature","submit_replication":"https://pith.science/pith/RQYXOFGLDOBB5VC5W3GK4GVLKK/action/replication_record"}},"created_at":"2026-07-05T08:46:10.803537+00:00","updated_at":"2026-07-05T08:46:10.803537+00:00"}