Voice Biomarkers for Depression and Anxiety

• URL: http://arxiv.org/abs/2605.09908v1
• Date: Mon, 11 May 2026 02:51:35 GMT
• Title: Voice Biomarkers for Depression and Anxiety
• Abstract summary: Current approaches to detecting depression and anxiety from speech rely on machine learning techniques.<n>Applying deep learning methods directly to raw speech signals has the potential to produce biomarker representations with substantially greater predictive power.<n>We present our efforts toward developing a deep learning model trained on a large-scale proprietary dataset.
• Score: 1.0535472555708638
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current approaches to detecting depression and anxiety from speech primarily rely on machine learning techniques that utilize hand-engineered paralinguistic features and related acoustic descriptors derived from time- and frequency-domain representations of speech signals. Applying deep learning methods directly to raw speech signals has the potential to produce biomarker representations with substantially greater predictive power. However, these approaches typically require large volumes of carefully annotated data to learn robust and clinically meaningful representations of the underlying biomarkers. In this paper, we describe our efforts toward developing a deep learning model trained on a large-scale proprietary dataset comprising ~65,000 utterances collected from more than 23,000 subjects representative of relevant United States demographics. We present the techniques employed and analyze their impact on model performance. Our results demonstrate that the proposed models can extract content-agnostic biomarker information, which, when combined with lexical features extracted from audio, yields improved predictive performance in production settings. Our models are evaluated on ~5000 unique subjects and achieve performance of 71% in terms of sensitivity and specificity. To foster further research in mental health assessment from speech, we release the best-performing model described in this paper on HuggingFace.

Related papers

• Depression Markers in Speech: An Approach based on Tract Variables Dynamics [52.72895760734978]
  This study identifies new depression biomarkers based on the dynamical properties of tract variables.<n>The proposed biomarkers effectively discriminate between the depressed and control speakers, as evidenced by the high Cliffs delta values across both read and spontaneous speech.
  arXiv  Detail & Related papers  (2026-07-28T15:48:07Z)
• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• TabPFN-Wide: Continued Pre-Training for Extreme Feature Counts [2.3448377994589644]
  We propose a strategy that extends existing models through continued pre-training on synthetic data sampled from a customized prior.<n>The resulting model, TabPFN-Wide, matches or exceeds its base model's performance while exhibiting improved robustness to noise.
  arXiv  Detail & Related papers  (2025-10-07T17:28:49Z)
• Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds [24.203596224724848]
  Self-supervised speech models have demonstrated impressive performance in speech processing, but their effectiveness on non-speech data remains underexplored.<n>We show that models such as HuBERT, WavLM, and XEUS can generate rich latent representations of animal sounds across taxa.<n>Results are competitive with fine-tuned bioacoustic pre-trained models and show the impact of noise-robust pre-training setups.
  arXiv  Detail & Related papers  (2025-09-04T12:39:05Z)
• Speech transformer models for extracting information from baby cries [0.6822819361110412]
  We evaluate five pre-trained speech models on eight baby cries datasets.<n>For each dataset, we assess the latent representations of each model across all available classification tasks.<n>Our results demonstrate that the latent representations of these models can effectively classify human baby cries.
  arXiv  Detail & Related papers  (2025-09-02T12:34:33Z)
• Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025 [64.59170359368699]
  We present a robust system for the INTERSPEECH 2025 Speech Emotion Recognition in Naturalistic Conditions Challenge.<n>Our method combines state-of-the-art audio models with text features enriched by prosodic and spectral cues.
  arXiv  Detail & Related papers  (2025-06-02T13:46:02Z)
• Measuring the Robustness of Audio Deepfake Detectors [59.09338266364506]
  This work systematically evaluates the robustness of 10 audio deepfake detection models against 16 common corruptions.<n>Using both traditional deep learning models and state-of-the-art foundation models, we make four unique observations.
  arXiv  Detail & Related papers  (2025-03-21T23:21:17Z)
• Robust Speech and Natural Language Processing Models for Depression Screening [0.0]
  Depression is a global health concern with a critical need for increased patient screening.<n>We have described two deep learning models developed for this purpose.<n>One model is based on acoustics; the other is based on natural language processing.
  arXiv  Detail & Related papers  (2024-12-26T06:05:52Z)
• Detecting Speech Abnormalities with a Perceiver-based Sequence Classifier that Leverages a Universal Speech Model [4.503292461488901]
  We propose a Perceiver-based sequence to detect abnormalities in speech reflective of several neurological disorders. We combine this sequence with a Universal Speech Model (USM) that is trained (unsupervised) on 12 million hours of diverse audio recordings. Our model outperforms standard transformer (80.9%) and perceiver (81.8%) models and achieves an average accuracy of 83.1%.
  arXiv  Detail & Related papers  (2023-10-16T21:07:12Z)
• Analysing the Impact of Audio Quality on the Use of Naturalistic Long-Form Recordings for Infant-Directed Speech Research [62.997667081978825]
  Modelling of early language acquisition aims to understand how infants bootstrap their language skills. Recent developments have enabled the use of more naturalistic training data for computational models. It is currently unclear how the sound quality could affect analyses and modelling experiments conducted on such data.
  arXiv  Detail & Related papers  (2023-05-03T08:25:37Z)
• Leveraging Pretrained Representations with Task-related Keywords for Alzheimer's Disease Detection [69.53626024091076]
  Alzheimer's disease (AD) is particularly prominent in older adults. Recent advances in pre-trained models motivate AD detection modeling to shift from low-level features to high-level representations. This paper presents several efficient methods to extract better AD-related cues from high-level acoustic and linguistic features.
  arXiv  Detail & Related papers  (2023-03-14T16:03:28Z)
• Decoding speech perception from non-invasive brain recordings [48.46819575538446]
  We introduce a model trained with contrastive-learning to decode self-supervised representations of perceived speech from non-invasive recordings. Our model can identify, from 3 seconds of MEG signals, the corresponding speech segment with up to 41% accuracy out of more than 1,000 distinct possibilities.
  arXiv  Detail & Related papers  (2022-08-25T10:01:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.