• Our laboratory focuses on three main application domains of artificial intelligence and speech technologies:
  education, healthcare, and finance. The team conducts research on large language models (LLMs), audio LLMs, speech recognition and synthesis,
  emotion and speaker analysis, natural language processing, and audio signal processing.

Education

Evaluation of reading fluency and reading comprehension skills in primary school children, and automatic measurement of accent and language proficiency levels in individuals learning Turkish as a foreign language.

Healthcare

Voice- and text-based screening systems for the early detection of depression and anxiety through speech and human–robot interactions in psychiatry.

Finance

AI-driven decision support systems for investment, personal digital advisory tools in banking, and robo-advisor applications based on artificial intelligence.

• Our research combines deep neural networks, statistical machine learning, big data analytics, and advanced programming methods in both theoretical and applied projects. The laboratory also leads the development of next-generation systems inemotional speech synthesis, voice assistant design, and human–machine interaction.