Anup Singh

I am currently an Applied Scientist at Amazon, where I work on Automatic Speech Recognition (ASR), leveraging large-scale models and speech LLMs to improve accuracy, robustness, and multilingual capabilities in real-world media applications. My broader interests include speech representation learning, audio understanding, and efficient large-scale systems.

I completed my Ph.D. in Computer Science at Ghent University, where I was part of the Speech and Audio Processing Group at IDLab. I was advised by Prof. Kris Demuynck and Prof. Vipul Arora. My doctoral research focused on self-supervised learning for speech and audio, with an emphasis on scalable audio indexing and retrieval. Building on this foundation, I explored speech tokenization techniques aimed at advancing textless NLP and speech-based language models.

I hold a BS–MS dual degree in Mathematics from the Indian Institute of Science Education and Research (IISER-Kolkata).

Outside of work, I enjoy learning about geopolitics, reading, and playing sports (mostly lawn-tennis these days!)