TriVector@DravidianLangTech 2026: Depression Detection from Tamil and Malayalam Speech with Speaker-Independent Evaluation using MFCC and Wav2Vec2
Domain:
natural language processingRecord type:
paper
Creator:
AssEidMurReb
Publisher:
Und
Host:
Depression is a major mental health concern that can be reflected through subtle changes in speech patterns, prosody, and vocal characteristics. In low-resource and multilingual settings, depression detection from speech may become particularly more challenging. In this work, we present our system for the Shared Task on Depression Detection from Malayalam and Tamil. We explored both handcrafted acoustic features (MFCC) and pretrained speech representations (Wav2Vec2) for depression detection, along with a simple fusion strategy to examine their complementary strengths. Our observations showed that Wav2Vec2 generalized better for Malayalam, whereas for Tamil, a validation-tuned probability fusion performed best. The final system achieved macro-F1 scores of 99.5% for Malayalam and 88.6% for Tamil, securing 3rd place in both tasks.
Similar
AITamilDialect@DravidianLangTech 2026: Zero-Shot Whisper and Wav2Vec2 Embedding-Based Tamil Speech Recognition and Dialect Classification.Azrael@DravidianLangTech 2026:Dialect-Sensitive Automatic Speech Recognition and Classification for TamilSarcasm detection in Tamil and Malayalam YouTube commentsCUET_SYNTHETICA@DravidianLangTech 2026: Multi Architecture Transformer Ensemble for Detecting Abusive Tamil Text Targeting WomenOne_by_zero@DravidianLangTech 2025: Fake News Detection in Malayalam Language Leveraging Transformer-based ApproachMultimodal Depression Detection from Speech and Text Using a Fusion Neural Network