{"ID":6544619,"CreatedAt":"2026-07-14T04:15:24.506794117Z","UpdatedAt":"2026-07-14T15:06:33.663243204Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02920","arxiv_id":"2607.02920","title":"Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment","abstract":"Significant disparities exist in the diagnosis and clinical presentation of depression across different linguistic populations. Speech-based depression detection performs well monolingually, but cross-lingual generalization remains an open challenge. A key reason is that prior work uses segment-level random splits without speaker grouping, leading to identity leakage that inflates reported metrics. We propose CLeaD, a supervised contrastive alignment framework that maps WavLM embeddings from English and Mandarin into a shared clinical space, without parallel data or target-language fine-tuning. Evaluating 52 Mandarin speakers, contrastive alignment modestly outperforms the baseline (F1: 0.640 vs. 0.622) under leave-one-speaker-out evaluation. It also improves depressed-class recall at intermediate layers (7-8), though the small test set limits generalizability. Two findings remain robust: model scaling degrades cross-lingual performance while improving monolingual English, and speaker identity leakage artificially inflated previously reported Mandarin F1 scores to 0.954, an artifact we reproduce and quantify.","short_abstract":"Significant disparities exist in the diagnosis and clinical presentation of depression across different linguistic populations. Speech-based depression detection performs well monolingually, but cross-lingual generalization remains an open challenge. A key reason is that prior work uses segment-level random splits with...","url_abs":"https://arxiv.org/abs/2607.02920","url_pdf":"https://arxiv.org/pdf/2607.02920v1","authors":"[\"Anisha Pattanayak\",\"Hanie Kang\",\"Huang-Cheng Chou\",\"Shrikanth Narayanan\",\"Sudarsana Reddy Kadiri\"]","published":"2026-07-03T03:24:38Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[]","has_code":false}