profile
For my full CV or additional details, please feel free to contact me directly.
Basics
Name | Md Mubtasim Ahasan |
mubtasimahasan@gmail.com | |
Url | https://mubtasimahasan.github.io/ |
Work
-
2024.10 - Present Dhaka, Bangladesh
Research Assistant
Center for Computational & Data Sciences (CCDS), Independent University, Bangladesh (IUB)
-
2024.03 - 2024.10 Dhaka, Bangladesh
Research Assistant (Part-Time)
Center for Computational & Data Sciences (CCDS), Independent University, Bangladesh (IUB)
-
2021.01 - 2022.01 Dhaka, Bangladesh
Undergraduate Research Student
Computing for Sustainability and Social Good (C2SG) Lab, Brac University
Education
-
2018.01 - 2022.05 Dhaka, Bangladesh
Publications
-
2025.8.21 DM-Codec: Distilling Multimodal Representations for Speech Tokenization
EMNLP 2025 (Findings)
We propose two novel distillation approaches: (1) a language model (LM)-guided distillation method that incorporates contextual information, and (2) a combined LM and self-supervised speech model (SM)-guided distillation technique that effectively distills multimodal representations (acoustic, semantic, and contextual) into a comprehensive speech tokenizer, termed DM-Codec. The DM-Codec architecture adopts a streamlined encoder-decoder framework with a Residual Vector Quantizer (RVQ) and incorporates the LM and SM during the training process. Experiments show DM-Codec significantly outperforms state-of-the-art speech tokenization models, reducing WER by up to 13.46%, WIL by 9.82%, and improving speech quality by 5.84% and intelligibility by 1.85% on the LibriSpeech benchmark dataset.
Languages
Bengali | |
Native speaker |
English | |
Fluent |