{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:32FBQTAI5TBSRPDRQEJ3OIEK3E","short_pith_number":"pith:32FBQTAI","schema_version":"1.0","canonical_sha256":"de8a184c08ecc328bc718113b7208ad93ececf6d667f7535167a7e0ec43d7c02","source":{"kind":"arxiv","id":"2408.13920","version":4},"attestation_state":"computed","paper":{"title":"Wav2Small: Distilling Wav2Vec2 to 72K parameters for Low-Resource Speech emotion recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Anna Derington, Bj\\\"orn Schuller, Dionyssos Kounadis-Bastian, Felix Burkhardt, Florian Eyben, Hagen Wierstorf, Oliver Schr\\\"ufer","submitted_at":"2024-08-25T19:13:56Z","abstract_excerpt":"Speech Emotion Recognition (SER) needs high computational resources to overcome the challenge of substantial annotator disagreement. Today SER is shifting towards dimensional annotations of arousal, dominance, and valence (A/D/V). Universal metrics as the L2 distance prove unsuitable for evaluating A/D/V accuracy due to non converging consensus of annotator opinions. However, Concordance Correlation Coefficient (CCC) arose as an alternative metric for A/D/V where a model's output is evaluated to match a whole dataset's CCC rather than L2 distances of individual audios. Recent studies have show"},"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":"2408.13920","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-25T19:13:56Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fb5b994fa96a203ca92c973b18a20aa69b206cace9b1a06f72437b342cc4ff9c","abstract_canon_sha256":"1665144ac3bac034e8c6c862513b263910d1f522b82909b6485eb06e6b714149"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:08.848365Z","signature_b64":"4i73ES3FJq9Uivtw9dq2yrhhwkp3NYbFJCS1yfm1voDdCGoD35tiuRBl24xKdM9dU9XD0GLduwrWdp8yk5LnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de8a184c08ecc328bc718113b7208ad93ececf6d667f7535167a7e0ec43d7c02","last_reissued_at":"2026-07-05T09:39:08.847890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:08.847890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wav2Small: Distilling Wav2Vec2 to 72K parameters for Low-Resource Speech emotion recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Anna Derington, Bj\\\"orn Schuller, Dionyssos Kounadis-Bastian, Felix Burkhardt, Florian Eyben, Hagen Wierstorf, Oliver Schr\\\"ufer","submitted_at":"2024-08-25T19:13:56Z","abstract_excerpt":"Speech Emotion Recognition (SER) needs high computational resources to overcome the challenge of substantial annotator disagreement. Today SER is shifting towards dimensional annotations of arousal, dominance, and valence (A/D/V). Universal metrics as the L2 distance prove unsuitable for evaluating A/D/V accuracy due to non converging consensus of annotator opinions. However, Concordance Correlation Coefficient (CCC) arose as an alternative metric for A/D/V where a model's output is evaluated to match a whole dataset's CCC rather than L2 distances of individual audios. Recent studies have show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13920","kind":"arxiv","version":4},"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/2408.13920/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":"2408.13920","created_at":"2026-07-05T09:39:08.847953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13920v4","created_at":"2026-07-05T09:39:08.847953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13920","created_at":"2026-07-05T09:39:08.847953+00:00"},{"alias_kind":"pith_short_12","alias_value":"32FBQTAI5TBS","created_at":"2026-07-05T09:39:08.847953+00:00"},{"alias_kind":"pith_short_16","alias_value":"32FBQTAI5TBSRPDR","created_at":"2026-07-05T09:39:08.847953+00:00"},{"alias_kind":"pith_short_8","alias_value":"32FBQTAI","created_at":"2026-07-05T09:39:08.847953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.00059","citing_title":"BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32FBQTAI5TBSRPDRQEJ3OIEK3E","json":"https://pith.science/pith/32FBQTAI5TBSRPDRQEJ3OIEK3E.json","graph_json":"https://pith.science/api/pith-number/32FBQTAI5TBSRPDRQEJ3OIEK3E/graph.json","events_json":"https://pith.science/api/pith-number/32FBQTAI5TBSRPDRQEJ3OIEK3E/events.json","paper":"https://pith.science/paper/32FBQTAI"},"agent_actions":{"view_html":"https://pith.science/pith/32FBQTAI5TBSRPDRQEJ3OIEK3E","download_json":"https://pith.science/pith/32FBQTAI5TBSRPDRQEJ3OIEK3E.json","view_paper":"https://pith.science/paper/32FBQTAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13920&json=true","fetch_graph":"https://pith.science/api/pith-number/32FBQTAI5TBSRPDRQEJ3OIEK3E/graph.json","fetch_events":"https://pith.science/api/pith-number/32FBQTAI5TBSRPDRQEJ3OIEK3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32FBQTAI5TBSRPDRQEJ3OIEK3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32FBQTAI5TBSRPDRQEJ3OIEK3E/action/storage_attestation","attest_author":"https://pith.science/pith/32FBQTAI5TBSRPDRQEJ3OIEK3E/action/author_attestation","sign_citation":"https://pith.science/pith/32FBQTAI5TBSRPDRQEJ3OIEK3E/action/citation_signature","submit_replication":"https://pith.science/pith/32FBQTAI5TBSRPDRQEJ3OIEK3E/action/replication_record"}},"created_at":"2026-07-05T09:39:08.847953+00:00","updated_at":"2026-07-05T09:39:08.847953+00:00"}