Erfan Loweimi
erfan loweimi

Dr Erfan Loweimi

  

Biography

Erfan Loweimi holds a part-time EPSRC Research Fellowship at School of Computing, Engineering & The Built Environment, and serves as a full-time Research Associate at the Machine Intelligence Laboratory, University of Cambridge (2022-). Prior to his current roles, he held Research Associate positions at King’s College London (2021-2023) and at the Centre for Speech Technology Research (CSTR), University of Edinburgh (2018-2021). He earned his PhD from the University of Sheffield in 2018, where he was a Faculty Scholar in the Speech and Hearing Research Group (SPandH), Department of Computer Science.

Erfan has received recognition for his contributions, including the “Research Communicator of the Year Award (University of Sheffield, 2017)” and the “Outstanding Reviewer Award (IEEE ICASSP, 2022).” He has actively served his community in various capacities, including as an Area Chair in prestigious conferences (INTERSPEECH, ICASSP, EMNLP), Publication Chair, Organising Committee Member in multiple conferences, and as an associate member of the IEEE’s Speech and Language Technical Committee (SLTC).

Dr. Loweimi has published 38 peer-reviewed papers and is the first author of more than 28 journal and conference papers, including three in IEEE Transactions on Audio, Speech, and Language Processing. His research interests encompass end-to-end speech processing and recognition, applications of speech technology in healthcare, explainable and trustworthy AI-based speech technology, multi-modal speech processing, and multi-modal information retrieval.

School

Research Groups

Esteem

Conference Organising Activity

  • Meta Reviewer in IEEE ICASSP 2024
  • Area Chair in ISCA INTERSPEECH 2024
  • UKISpeech 2024 Co-organiser
  • Area Chair in ISCA INTERSPEECH 2023
  • Area Chair in EMNLP 2023
  • Meta Reviewer in IEEE ICASSP 2023
  • Publication Chair in IEEE Spoken Language Technology Workshop (SLT)
  • UKSpeech 2016 co-organiser

 

Fellowships and Awards

  • Outstanding Reviewer Award (IEEE ICASSP 2022)
  • Research Communicator of the Year Award (University of Sheffield, 2017)

 

Invited Speaker

  • Speaker Retrieval in the Wild, BBC Broadcasting House, London, UK, 2024
  • Speaker Retrieval in the Wild: Challenges, Effectiveness and Robustness, University of Cambridge, Cambridge, UK, 2024
  • Phonetic Error Analysis beyond Phone Error Rate, University of Edinburgh, Edinburgh, UK, 2023
  • Recent Advances in Interpreting and Understanding DNNs, Iranian Conference on Machine Vision and Image Processing (MVIP), Iran, 2022
  • Speech Acoustic Modelling from Raw Signal Representations, Edinburgh Napier University, Edinburgh, UK, 2022
  • On the Robustness and Training Dynamics of Raw Waveform Models, University of Edinburgh, Edinburgh, UK, 2021
  • Raw Sign and Magnitude Spectra for Multi-head Acoustic Modelling, University of Edinburgh, Edinburgh, UK, 2020
  • DNN Statistical Interpretation and Normalisation for ASR, University of Edinburgh, Edinburgh, UK, 2019
  • Understanding and Interpreting DNNs for Speech Recognition, Qatar Computing Research Institute (QCRI), Doha, Qatar, 2019
  • Robust Phase-based Speech Signal Processing; From Source-Filter Separation to Model-Based Robust ASR, University of Sheffield, Sheffield, UK, 2018
  • Speech Phase Spectrum: Love It or Leave It?, University of Edinburgh, Edinburgh, UK, 2018
  • Genie in the mike! The Science of Talking (with) Machines, A Pint of Science Festival, Sheffield, 2017
  • Channel Compensation in the Generalised VTS Approach to Robust ASR, UKSpeech 2017, University of Cambridge, Cambridge, UK, 2017
  • Signal Processing is Dead(?)! Long Live DNN!, Machine Intelligence for Natural Interfaces (MINI) workshop, Sheffield, 2016
  • Deep Learning, The End of History and The Last Computer Scientist, A Pint of Science Festival, Sheffield, 2016
  • Source-filter Separation of Speech Signal in the Phase Domain, UKSpeech 2015, University of East Anglia, Norwich, UK, 2015

 

Membership of Professional Body

  • IEEE Signal Processing Society
  • International Speech Communication Association (ISCA)

 

Public/Community Engagement

  • Genie in the mike! The Science of Talking (with) Machines, A Pint of Science Festival, Sheffield, UK, 2017
  • Deep Learning, The End of History and The Last Computer Scientist, A Pint of Science Festival, Sheffield, UK, 2016

 

Reviewing

  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • International Conference on Affective Computing & Intelligent Interaction (ACII)
  • IEEE Automatic Speech and Understanding Workshop (ASRU)
  • Computer Speech & Language
  • IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • ISCA INTERSPEECH

 

Visiting Positions

  • Visitor in King's College London (KCL)
  • Visitor in Centre for Speech Technology Research (CSTR), University of Edinburgh

 

Filter by

Date


29 results

Windowed Attention Mechanisms for Speech Recognition

Conference Proceeding
Zhang, S., Loweimi, E., Bell, P., & Renals, S. (2019)
Windowed Attention Mechanisms for Speech Recognition. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2019.8682224
The usual attention mechanisms used for encoder-decoder models do not constrain the relationship between input and output sequences to be monotonic. To address this we explore...

Exploring the Use of Group Delay for Generalised VTS Based Noise Compensation

Conference Proceeding
Loweimi, E., Barker, J., & Hain, T. (2018)
Exploring the Use of Group Delay for Generalised VTS Based Noise Compensation. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2018.8462595
In earlier work we studied the effect of statistical normalisation for phase-based features and observed it leads to a significant robustness improvement. This paper explores ...

On the Usefulness of the Speech Phase Spectrum for Pitch Extraction

Conference Proceeding
Loweimi, E., Barker, J., & Hain, T. (2018)
On the Usefulness of the Speech Phase Spectrum for Pitch Extraction. In Proc. Interspeech 2018 (696-700). https://doi.org/10.21437/interspeech.2018-1062
Most frequency domain techniques for pitch extraction such as cepstrum, harmonic product spectrum (HPS) and summation residual harmonics (SRH) operate on the magnitude spectru...

Robust Source-Filter Separation of Speech Signal in the Phase Domain

Conference Proceeding
Loweimi, E., Barker, J., Torralba, O. S., & Hain, T. (2017)
Robust Source-Filter Separation of Speech Signal in the Phase Domain. In Proc. Interspeech 2017 (414-418). https://doi.org/10.21437/interspeech.2017-210
In earlier work we proposed a framework for speech source-filter separation that employs phase-based signal processing. This paper presents a further theoretical investigation...

Channel Compensation in the Generalised Vector Taylor Series Approach to Robust ASR

Conference Proceeding
Loweimi, E., Barker, J., & Hain, T. (2017)
Channel Compensation in the Generalised Vector Taylor Series Approach to Robust ASR. In Proc. Interspeech 2017 (2466-2470). https://doi.org/10.21437/interspeech.2017-211
Vector Taylor Series (VTS) is a powerful technique for robust ASR but, in its standard form, it can only be applied to log-filter bank and MFCC features. In earlier work, we p...

Statistical normalisation of phase-based feature representation for robust speech recognition

Conference Proceeding
Loweimi, E., Barker, J., & Hain, T. (2017)
Statistical normalisation of phase-based feature representation for robust speech recognition. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2017.7953170
In earlier work we have proposed a source-filter decomposition of speech through phase-based processing. The decomposition leads to novel speech features that are extracted fr...

Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition

Conference Proceeding
Loweimi, E., Barker, J., & Hain, T. (2016)
Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition. In Proc. Interspeech 2016 (3798-3802). https://doi.org/10.21437/interspeech.2016-1028
Designing good normalisation to counter the effect of environmental distortions is one of the major challenges for automatic speech recognition (ASR). The Vector Taylor series...

Source-filter separation of speech signal in the phase domain

Conference Proceeding
Loweimi, E., Barker, J., & Hain, T. (2015)
Source-filter separation of speech signal in the phase domain. In Proc. Interspeech 2015 (598-602). https://doi.org/10.21437/interspeech.2015-211
Deconvolution of the speech excitation (source) and vocal tract (filter) components through log-magnitude spectral processing is well-established and has led to the well-known...

A new phase-based feature representation for robust speech recognition

Conference Proceeding
Loweimi, E., Ahadi, S. M., & Drugman, T. (2013)
A new phase-based feature representation for robust speech recognition. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. https://doi.org/10.1109/icassp.2013.6639051
The aim of this paper is to introduce a novel phase-based feature representation for robust speech recognition. This method consists of four main parts: autoregressive (AR) mo...