Skip to content

WORK

CASE_STUDIES — WORKPLACE PROJECTS

2026FYI.AIML engineering

Speech Emotion Recognition on Open-Source Orukeet

77.4%Accuracy on speakers never heard in training
+3.8 ptsAhead of emotion2vec+, the best open-source baseline
0.2 sTo analyse a 10–15 s clip on GPU
2026FYI.AIML engineering

Teaching a Voice Model to Cough, Sigh and Laugh

8New expression tags, each its own token in the model
111 hTraining audio from 7 speech corpora
0Tag words read out loud across 180 test clips