StressSpeak: A Speech-Driven Framework for Real-Time Personalized Stress Detection and Adaptive Psychological Support

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21260%2F25%3A00386562" target="_blank" >RIV/68407700:21260/25:00386562 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.3390/diagnostics15222871" target="_blank" >https://doi.org/10.3390/diagnostics15222871</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/diagnostics15222871" target="_blank" >10.3390/diagnostics15222871</a>

Result language

angličtina

Original language name

StressSpeak: A Speech-Driven Framework for Real-Time Personalized Stress Detection and Adaptive Psychological Support

Original language description

Abstract: Background: Stress is a critical determinant of mental health, yet conventional monitoring approaches often rely on subjective self-reports or physiological signals that lack real-time responsiveness. Recent advances in large language models (LLMs) offer opportunities for speech-driven, adaptive stress detection, but existing systems are limited to retrospective text analysis, monolingual settings, or detection-only outputs. Methods: We developed a real-time, speech-driven stress detection framework that integrates audio recording, speech-to-text conversion, and linguistic analysis using transformer-based LLMs. The system provides multimodal outputs, delivering recommendations in both text and synthesized speech. Nine LLM variants were evaluated on five benchmark datasets under zero-shot and few-shot learning conditions. Performance was assessed using accuracy, precision, recall, F1-score, and misclassification trends (false-negatives and false-positives). Real-time feasibility was analyzed through latency modeling, and user-centered validation was conducted across cross-domains. Results: Few-shot fine-tuning improved model performance across all datasets, with Large Language Model Meta AI (LLaMA) and Robustly Optimized BERT Pretraining Approach (RoBERTa) achieving the highest F1-scores and reduced false-negatives, particularly for suicide risk detection. Latency analysis revealed a trade-off between responsiveness and accuracy, with delays ranging from ~2 s for smaller models to ~7.6 s for LLaMA-7B on 30 s audio inputs. Multilingual input support and multimodal output enhanced inclusivity. User feedback confirmed strong usability, accessibility, and adoption potential in real-world settings. Conclusions: This study demonstrates that real-time, LLM-powered stress detection is both technically robust and practically feasible. By combining speech-based input, multimodal feedback, and user-centered validation, the framework advances beyond traditional detection only models toward scalable, inclusive, and deployment-ready digital mental health solutions.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

30404 - Biomaterials (as related to medical implants, devices, sensors)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Diagnostics

ISSN

2075-4418

e-ISSN

2075-4418

Volume of the periodical

15

Issue of the periodical within the volume

22

Country of publishing house

CH - SWITZERLAND

Number of pages

20

Pages from-to

—

UT code for WoS article

001625946300001

EID of the result in the Scopus database

2-s2.0-105023075914