Muhammad Umar Farooq
Doctoral reseracher, Speech processing
I am a doctoral student at the Department of Computer Science, University of Sheffield (UK) since 2021. I am working on multilingual speech recognition systems at LivePerson centre for Speech and Language Technologies (SLT)
under supervision of Prof. Thomas Hain. My PhD reserach revolves around cross-lingual acoustic-phonetic similarities. Being part of LivePerson centre, I am also associated with Speech and Hearing (SPANDH), and Machine Intelligence for Natural Interfaces (MINI) reserach groups.
Alongside my PhD, I am also working as Graduate Teaching Assistant (GTA) for various modules at University of Sheffield. Currently, I am assisting teachers for Machine Learning and Adaptive Intelligence, and Data Science with Python. Please visit the teaching page for details.
Before enrolling for my Ph.D., I was a pre-doc research intern at Institute of Formal and Applied Linguistics (UFAL), Charles University, Prague. I primarily worked on speech related components of EU Horizon 2020 project European Live Translator (ELITR)
supervised by Dr. Ondrej Bojar.
Prior to joining the UFAL, I have been working as speech processing Research Officer at Center for Language Engineering (CLE), University of Engineering and Technology (UET), Lahore. I joined CLE during my senior year as a speech scientist to develop low resource language technologies in supervision of Dr. Sarmad Hussain. I received my M.Sc. and B.Sc. Electrical Engineering degrees from UET, Lahore in 2019 and 2017 respectively.
Selected Publications
- Progressive Unsupervised Domain Adaptation for ASR Using Ensemble Models and Multi-stage TrainingIn accepted for ICASSP, 2024
- Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech RecognitionIn Proc. INTERSPEECH, 2023
- Towards Domain Generalisation in ASR with Elitist Sampling and Ensemble Knowledge DistillationIn ICASSP, 2023
- Investigating the Impact of Crosslingual Acoustic-Phonetic Similarities on Multilingual Speech RecognitionIn Proc. Interspeech, 2022
- Non-Linear Pairwise Language Mappings for Low-Resource Multilingual Acoustic Model FusionIn Proc. Interspeech, 2022
- Improving Large Vocabulary Urdu Speech Recognition System Using Deep Neural NetworksIn Proc. Interspeech 2019, 2019