Erfan Loweimi

According to our database, Erfan Loweimi authored at least 37 papers between 2010 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Multi-Stream Acoustic Modelling Using Raw Real and Imaginary Parts of the Fourier Transform.

Erfan Loweimi, Zhengjun Yue, Peter Bell, Steve Renals, Zoran Cvetkovic

IEEE ACM Trans. Audio Speech Lang. Process., 2023

Phonetic Error Analysis Beyond Phone Error Rate.

Erfan Loweimi, Andrea Carmantini, Peter Bell, Steve Renals, Zoran Cvetkovic

IEEE ACM Trans. Audio Speech Lang. Process., 2023

Zero-shot Audio Topic Reranking using Large Language Models.

Mengjie Qian, Rao Ma, Adian Liusie, Erfan Loweimi, Kate M. Knill, Mark J. F. Gales

CoRR, 2023

2022

Acoustic Modelling From Raw Source and Filter Components for Dysarthric Speech Recognition.

Zhengjun Yue, Erfan Loweimi, Heidi Christensen, Jon Barker, Zoran Cvetkovic

IEEE ACM Trans. Audio Speech Lang. Process., 2022

Dysarthric Speech Recognition From Raw Waveform with Parametric CNNs.

Zhengjun Yue, Erfan Loweimi, Heidi Christensen, Jon Barker, Zoran Cvetkovic

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

RCT: Random consistency training for semi-supervised sound event detection.

Nian Shao, Erfan Loweimi, Xiaofei Li

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Multi-Modal Acoustic-Articulatory Feature Fusion For Dysarthric Speech Recognition.

Zhengjun Yue, Erfan Loweimi, Zoran Cvetkovic, Heidi Christensen, Jon Barker

Proceedings of the IEEE International Conference on Acoustics, 2022

Raw Source and Filter Modelling for Dysarthric Speech Recognition.

Zhengjun Yue, Erfan Loweimi, Zoran Cvetkovic

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

On The Usefulness of Self-Attention for Automatic Speech Recognition with Transformers.

Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals

Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Stochastic Attention Head Removal: A Simple and Effective Method for Improving Transformer Based ASR Models.

Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Speech Acoustic Modelling Using Raw Source and Filter Components.

Erfan Loweimi, Zoran Cvetkovic, Peter Bell, Steve Renals

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Train Your Classifier First: Cascade Neural Networks Training from Upper Layers to Lower Layers.

Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals

Proceedings of the IEEE International Conference on Acoustics, 2021

Speech Acoustic Modelling from Raw Phase Spectrum.

Erfan Loweimi, Zoran Cvetkovic, Peter Bell, Steve Renals

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Stochastic Attention Head Removal: A Simple and Effective Method for Improving Automatic Speech Recognition with Transformers.

Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals

CoRR, 2020

When Can Self-Attention Be Replaced by Feed Forward Layers?

Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals

CoRR, 2020

Raw Sign and Magnitude Spectra for Multi-Head Acoustic Modelling.

Erfan Loweimi, Peter Bell, Steve Renals

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

On the Robustness and Training Dynamics of Raw Waveform Models.

Erfan Loweimi, Peter Bell, Steve Renals

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

2019

Trainable Dynamic Subsampling for End-to-End Speech Recognition.

Shucong Zhang, Erfan Loweimi, Yumo Xu, Peter Bell, Steve Renals

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

On Learning Interpretable CNNs with Parametric Modulated Kernel-Based Filters.

Erfan Loweimi, Peter Bell, Steve Renals

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Learning Temporal Clusters Using Capsule Routing for Speech Emotion Recognition.

Md Asif Jalal, Erfan Loweimi, Roger K. Moore, Thomas Hain

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Windowed Attention Mechanisms for Speech Recognition.

Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals

Proceedings of the IEEE International Conference on Acoustics, 2019

On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition.

Erfan Loweimi, Peter Bell, Steve Renals

Proceedings of the IEEE International Conference on Acoustics, 2019

Acoustic Model Adaptation from Raw Waveforms with Sincnet.

Joachim Fainberg, Ondrej Klejch, Erfan Loweimi, Peter Bell, Steve Renals

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018

Robust phase-based speech signal processing from source-filter separation to model-based robust ASR.

Erfan Loweimi

PhD thesis, 2018

On the Usefulness of the Speech Phase Spectrum for Pitch Extraction.

Erfan Loweimi, Jon Barker, Thomas Hain

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

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

Erfan Loweimi, Jon Barker, Thomas Hain

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

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

Erfan Loweimi, Jon Barker, Oscar Saz-Torralba, Thomas Hain

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

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

Erfan Loweimi, Jon Barker, Thomas Hain

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

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

Erfan Loweimi, Jon Barker, Thomas Hain

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

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

Erfan Loweimi, Jon Barker, Thomas Hain

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

2015

Long-Term Statistical Feature Extraction from Speech Signal and Its Application in Emotion Recognition.

Erfan Loweimi, Mortaza Doulaty, Jon Barker, Thomas Hain

Proceedings of the Statistical Language and Speech Processing, 2015

Source-filter separation of speech signal in the phase domain.

Erfan Loweimi, Jon Barker, Thomas Hain

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

2013

On the Importance of Pre-emphasis and Window Shape in Phase-Based Speech Recognition.

Erfan Loweimi, Seyed Mohammad Ahadi, Thomas Drugman, Samira Loveymi

Proceedings of the Advances in Nonlinear Speech Processing - 6th International Conference, 2013

A new phase-based feature representation for robust speech recognition.

Erfan Loweimi, Seyed Mohammad Ahadi, Thomas Drugman

Proceedings of the IEEE International Conference on Acoustics, 2013

2011

Phase-Only Speech Reconstruction Using Very Short Frames.

Erfan Loweimi, Seyed Mohammad Ahadi, Hamid Sheikhzadeh

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

A new group delay-based feature for robust speech recognition.

Erfan Loweimi, Seyed Mohammad Ahadi

Proceedings of the 2011 IEEE International Conference on Multimedia and Expo, 2011

2010

Objective evaluation of phase and magnitude only reconstructed speech: New considerations.

Erfan Loweimi, Seyed Mohammad Ahadi

Proceedings of the 10th International Conference on Information Sciences, 2010