Pith. sign in

This paper investigates unifying diverse speech tasks within a single model for cross-task suicide risk detection

CONCLUSIONS For automatic suicide risk detection from spontaneous speech, participants are typically asked to complete multiple speech-based assessment tasks, the model per

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

citation-role summary

background 1

citation-polarity summary

support 1

fields

eess.AS 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

support 1

representative citing papers

Towards Paradigm-General Suicide Risk Detection via Speech LLM

eess.AS · 2025-09-26 · conditional · novelty 5.0

A speech LLM with a mixture of DoRA experts (MoDE) improves cross-task suicide risk detection accuracy (0.656 vs 0.635 joint tuning) and calibration on 1,223 Chinese adolescents across ten speech tasks, though the unseen-paradigm generalization claim is untested.

citing papers explorer

Showing 1 of 1 citing paper.

  • Towards Paradigm-General Suicide Risk Detection via Speech LLM eess.AS · 2025-09-26 · conditional · none · ref 5

    A speech LLM with a mixture of DoRA experts (MoDE) improves cross-task suicide risk detection accuracy (0.656 vs 0.635 joint tuning) and calibration on 1,223 Chinese adolescents across ten speech tasks, though the unseen-paradigm generalization claim is untested.