Shivam Akhouri

Vellore Institute of Technology University

Papers

Total Citations

H-Index

About

Shivam Akhouri is an emerging researcher at the intersection of speech processing and artificial intelligence, with a primary focus on emotion-aware speech synthesis and recognition. His most notable contribution, "EmoSRE: Emotion prediction based speech synthesis and refined speech recognition using large language model and prosody encoding" (2025), introduces a novel framework that integrates large language models with prosody encoding to simultaneously predict emotional states from speech and enhance recognition accuracy. This work, already garnering 4 citations shortly after publication, demonstrates his ability to bridge affective computing with practical speech technologies. Akhouri’s research addresses critical challenges in human-computer interaction, aiming to make synthetic speech more natural and responsive to emotional context. While early in his career, his innovative approach to combining LLMs with prosodic features signals a promising trajectory in advancing emotionally intelligent speech systems. His work holds potential for applications in virtual assistants, mental health monitoring, and adaptive communication tools, marking him as a rising voice in the field of speech AI.