{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QSUYQAKSPWX3ZDAPVOSC777A55","short_pith_number":"pith:QSUYQAKS","schema_version":"1.0","canonical_sha256":"84a98801527dafbc8c0faba42fffe0ef5e36e93b4619228c97356d853dc43cca","source":{"kind":"arxiv","id":"2606.27543","version":1},"attestation_state":"computed","paper":{"title":"Advancing Speaker-Based Vocal Effort Classification with WavLM and Data Augmentation in Naturalistic Non-Calibrated Speech Recordings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"John H. L. Hansen, Zahra Omidi","submitted_at":"2026-06-25T20:46:48Z","abstract_excerpt":"The variations in vocal effort range (e.g. whisper, soft, neutral, loud, shout) alter production and speech acoustics, reducing intelligibility and limiting the robustness of any subsequent speech technology. Classification is challenging since effort lies on a continuum, adjacent categories are easily confused, and labeled data remain scarce. Prior SSL approaches with wav2vec2, HuBERT, and AST improve performance on the AVID corpus but still suffer from boundary errors. In this study, we introduce WavLM for the first time in vocal effort classification and benchmark it against wav2vec2 and Hu"},"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":"2606.27543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T20:46:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"59a3478f64e103bc568bdc52e744af8b1bc85d4f34b357b868c0f06351bafac0","abstract_canon_sha256":"e0869c69160d211e8fd392296ab0e656c280eb2a5599655d5f478fd1a26cea0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:09.568151Z","signature_b64":"2LzhMLVPl54H1Ypbw3bkDbiEkcQ311Hg0rgRelng8OrK1RbOhRSJjkxQXyXSjW2L0iEbU4rZmuMF5CxHpfOaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84a98801527dafbc8c0faba42fffe0ef5e36e93b4619228c97356d853dc43cca","last_reissued_at":"2026-06-29T00:14:09.567750Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:09.567750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Speaker-Based Vocal Effort Classification with WavLM and Data Augmentation in Naturalistic Non-Calibrated Speech Recordings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"John H. L. Hansen, Zahra Omidi","submitted_at":"2026-06-25T20:46:48Z","abstract_excerpt":"The variations in vocal effort range (e.g. whisper, soft, neutral, loud, shout) alter production and speech acoustics, reducing intelligibility and limiting the robustness of any subsequent speech technology. Classification is challenging since effort lies on a continuum, adjacent categories are easily confused, and labeled data remain scarce. Prior SSL approaches with wav2vec2, HuBERT, and AST improve performance on the AVID corpus but still suffer from boundary errors. In this study, we introduce WavLM for the first time in vocal effort classification and benchmark it against wav2vec2 and Hu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27543","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/2606.27543/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":"2606.27543","created_at":"2026-06-29T00:14:09.567811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27543v1","created_at":"2026-06-29T00:14:09.567811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27543","created_at":"2026-06-29T00:14:09.567811+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSUYQAKSPWX3","created_at":"2026-06-29T00:14:09.567811+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSUYQAKSPWX3ZDAP","created_at":"2026-06-29T00:14:09.567811+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSUYQAKS","created_at":"2026-06-29T00:14:09.567811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.27543","citing_title":"Advancing Speaker-Based Vocal Effort Classification with WavLM and Data Augmentation in Naturalistic Non-Calibrated Speech Recordings","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSUYQAKSPWX3ZDAPVOSC777A55","json":"https://pith.science/pith/QSUYQAKSPWX3ZDAPVOSC777A55.json","graph_json":"https://pith.science/api/pith-number/QSUYQAKSPWX3ZDAPVOSC777A55/graph.json","events_json":"https://pith.science/api/pith-number/QSUYQAKSPWX3ZDAPVOSC777A55/events.json","paper":"https://pith.science/paper/QSUYQAKS"},"agent_actions":{"view_html":"https://pith.science/pith/QSUYQAKSPWX3ZDAPVOSC777A55","download_json":"https://pith.science/pith/QSUYQAKSPWX3ZDAPVOSC777A55.json","view_paper":"https://pith.science/paper/QSUYQAKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27543&json=true","fetch_graph":"https://pith.science/api/pith-number/QSUYQAKSPWX3ZDAPVOSC777A55/graph.json","fetch_events":"https://pith.science/api/pith-number/QSUYQAKSPWX3ZDAPVOSC777A55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSUYQAKSPWX3ZDAPVOSC777A55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSUYQAKSPWX3ZDAPVOSC777A55/action/storage_attestation","attest_author":"https://pith.science/pith/QSUYQAKSPWX3ZDAPVOSC777A55/action/author_attestation","sign_citation":"https://pith.science/pith/QSUYQAKSPWX3ZDAPVOSC777A55/action/citation_signature","submit_replication":"https://pith.science/pith/QSUYQAKSPWX3ZDAPVOSC777A55/action/replication_record"}},"created_at":"2026-06-29T00:14:09.567811+00:00","updated_at":"2026-06-29T00:14:09.567811+00:00"}