Kadri Hacioglu

Context Projector: Complementary Keyword and Dialogue Context Embeddings for LLM-based ASR

Reading Emotions in the Token Space: Discriminative Adaptation of SpeechLLMs for Emotion Recognition

SpeechLLMs have shown strong potential for emotion recognition, yet they read the predicted emotion off a generative decoder not suited for classification: it can emit labels outside the target set and favors frequent classes. We propose a discriminative adaptation that reads the final prompt token's hidden state throu...

Less can be More: What Aspects of Speech Drive End-of-Turn Detection

These findings suggest that turn-taking is primarily conveyed through intonation and silence patterns rather than semantic completeness, enabling faster and more reliable systems without expensive text inference.