Speech Biomarkers in Psychiatry

A wide range of psychiatric disorders, including schizophrenia spectrum disorders, major depressive disorder, bipolar disorder, and other conditions affecting cognition, affect, and social communication impact millions worldwide and pose significant diagnostic and monitoring challenges. Traditional assessment methods rely heavily on subjective self-report, clinical interviews, and intermittent observation, all of which are vulnerable to recall bias, stigma, symptom fluctuation, and limited clinical contact time.

Recent technological advances in digital signal processing and machine learning have enabled the extraction of objective acoustic, prosodic, and linguistic features from speech that reflect underlying neurobiological and psychopathological states. Alterations in prosody, speech timing, vocal energy, semantic coherence, and linguistic content among others have been documented for mood disorders, schizophrenia spectrum disorders, and other psychiatric conditions. These speech patterns show promise as quantifiable, non-invasive digital biomarkers that may index psychomotor, cognitive, affective, and social-cognitive processes relevant across diagnostic categories. The integration of smartphone technology, wearable devices and remote monitoring platforms has made continuous, ecologically valid speech data collection increasingly feasible, opening new avenues for early detection, symptom tracking, and personalized intervention across a broad range of psychiatric disorders.

This Research Topic aims to advance our understanding of speech-based digital biomarkers across psychiatric disorders and accelerate their translation into clinical practice. Despite promising preliminary findings, significant gaps remain in standardizing measurement protocols, validating biomarkers across diverse populations, and establishing clinical utility. We seek to bring together multidisciplinary research exploring the neurobiological, cognitive, and linguistic mechanisms linking psychiatric symptomatology to changes in speech; developing and validating robust speech analysis algorithms; and evaluating their implementation in clinical workflows.

Key objectives include identifying which speech features most reliably correlate with symptom dimensions and treatment response, understanding how speech biomarkers perform across different demographic groups and cultural contexts, exploring the integration of speech analysis with other digital and traditional biomarkers, and evaluating the acceptability and feasibility of speech-based monitoring from patient and clinician perspectives. Recent advances in artificial intelligence, natural language processing, and accessible recording technologies position the field to make substantial progress toward objective, scalable tools that can enhance diagnosis, predict relapse, and guide personalized treatment strategies across psychiatric disorders.

This Research Topic welcomes contributions addressing speech biomarkers across psychiatric disorders, specifically depression, bipolar disorder, and schizophrenia spectrum disorders. We encourage submissions exploring:

- Acoustic and prosodic features;
- Natural language processing and semantic analysis of speech content;
- Machine learning and AI approaches for detecting and predicting psychiatric states using speech;
- Neurobiological mechanisms linking psychopathology to speech production;
- Validation studies across diagnoses, populations, languages, and cultural contexts;
- Longitudinal studies on speech changes associated with symptom progression, remission, and treatment response;
- Implementation and usability of speech-based monitoring in clinical and real-world settings.

We welcome Original Research articles, Systematic Reviews, Mini Reviews, Methods papers, and Perspective articles that advance the field of speech-based biomarkers toward clinical translation.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Case Report
• Clinical Trial
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• Methods
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Case Report
• Clinical Trial
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review
• Study Protocol
• Systematic Review

Keywords: speech acoustics, linguistics, mood disorders, digital biomarkers, machine learning, Schizophrenia

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.