Rehan Ahmad

Rehan Ahmad

Rehan Ahmad

Researchers, VoiceBase

I am a research associate in VoiceBaseteam of SpandH group at the university of Sheffield. I am working on semi-supervised learning for automatic speech recognition. My PhD dissertation was based on a multi-modal speaker diarization using an audio-visual synchronization model for active speaker detection. My interests are in speech signal processing, machine learning and computer vision. Before joining this group I served in many universities of Pakistan for teaching and research.

Publications

2024

Rehan Ahmad; Muhammad Umar Farooq; Thomas Hain: Progressive Unsupervised Domain Adaptation for ASR Using Ensemble Models and Multi-stage Training. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Forthcoming. (Type: Proceedings Article | )

2023

Muhammad Umar Farooq; Rehan Ahmad; Thomas Hain: MUST: A Multilingual Student-Teacher Approach for Low-Resource Speech Recognition. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2023. (Type: Proceedings Article | Links)
Rehan Ahmad; Md Asif Jalal; Muhammad Umar Farooq; Anna Ollerenshaw; Thomas Hain: Towards Domain Generalisation in ASR with Elitist Sampling and Ensemble Knowledge Distillation. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023, IEEE, 2023. (Type: Proceedings Article | Links)

2022

Chanho Park; Rehan Ahmad; Thomas Hain: Unsupervised Data Selection for Speech Recognition with Contrastive Loss Ratios. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8587-8591, 2022. (Type: Proceedings Article | Links)

Back to Top