Erfan Loweimi - RankMe

51 papers A 20C 1Misc 9Journal 15Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Raw acoustic-articulatory multimodal dysarthric speech recognition. Comput. Speech Lang. Zhengjun Yue, Erfan Loweimi, Zoran Cvetkovic, Jon Barker, Heidi Christensen
2025	A	`conf`	Challenges and practical guidelines for atypical speech data collection, annotation, usage and sharing: A multi-project perspective. INTERSPEECH Zhengjun Yue, Mara Barberis, Tanvina Patel, Judith Dineley, Willemijn Doedens, Lottie Stipdonk, Yuanyuan Zhang, Elke De Witte, Erfan Loweimi, Hugo Van hamme, Djaina Satoer, Marina B. Ruiter, Laureano Moro-Velázquez, Nicholas Cummins, Odette Scharenborg
2025	J	`jnl`	Probing Whisper for Dysarthric Speech in Detection and Assessment. CoRR Zhengjun Yue, Devendra Kayande, Zoran Cvetkovic, Erfan Loweimi
2025	J	`jnl`	Speaker Retrieval in the Wild: Challenges, Effectiveness and Robustness. CoRR Erfan Loweimi, Mengjie Qian, Kate M. Knill, Mark J. F. Gales
2025	A	`conf`	Zero-Shot Speech-Based Depression and Anxiety Assessment with LLMs. INTERSPEECH Erfan Loweimi, Sofia de la Fuente Garcia, Saturnino Luz
2024	J	`jnl`	Multi-modal video search by examples - A video quality impact analysis. IET Comput. Vis. Guanfeng Wu, Abbas Haider, Xing Tian, Erfan Loweimi, Chi-Ho Chan, Mengjie Qian, Muhammad Junaid Awan, Ivor T. A. Spence, Rob Cooper, Wing W. Y. Ng, Josef Kittler, Mark J. F. Gales, Hui Wang
2024	A	`conf`	On the Usefulness of Speaker Embeddings for Speaker Retrieval in the Wild: A Comparative Study of x-vector and ECAPA-TDNN Models. INTERSPEECH Erfan Loweimi, Mengjie Qian, Kate M. Knill, Mark J. F. Gales
2024	J	`jnl`	Phonetic Error Analysis of Raw Waveform Acoustic Models with Parametric and Non-Parametric CNNs. CoRR Erfan Loweimi, Andrea Carmantini, Peter Bell, Steve Renals, Zoran Cvetkovic
2024	—	`conf`	Zero-Shot Audio Topic Reranking Using Large Language Models. SLT Mengjie Qian, Rao Ma, Adian Liusie, Erfan Loweimi, Kate M. Knill, Mark J. F. Gales
2023	A	`conf`	Dysarthric Speech Recognition, Detection and Classification using Raw Phase and Magnitude Spectra. INTERSPEECH Zhengjun Yue, Erfan Loweimi, Zoran Cvetkovic
2023	J	`jnl`	Multi-Stream Acoustic Modelling Using Raw Real and Imaginary Parts of the Fourier Transform. IEEE ACM Trans. Audio Speech Lang. Process. Erfan Loweimi, Zhengjun Yue, Peter Bell, Steve Renals, Zoran Cvetkovic
2023	J	`jnl`	Phonetic Error Analysis Beyond Phone Error Rate. IEEE ACM Trans. Audio Speech Lang. Process. Erfan Loweimi, Andrea Carmantini, Peter Bell, Steve Renals, Zoran Cvetkovic
2023	J	`jnl`	Zero-shot Audio Topic Reranking using Large Language Models. CoRR Mengjie Qian, Rao Ma, Adian Liusie, Erfan Loweimi, Kate M. Knill, Mark J. F. Gales
2022	J	`jnl`	Acoustic Modelling From Raw Source and Filter Components for Dysarthric Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. Zhengjun Yue, Erfan Loweimi, Heidi Christensen, Jon Barker, Zoran Cvetkovic
2022	A	`conf`	Dysarthric Speech Recognition From Raw Waveform with Parametric CNNs. INTERSPEECH Zhengjun Yue, Erfan Loweimi, Heidi Christensen, Jon Barker, Zoran Cvetkovic
2022	Misc	`conf`	Multi-Modal Acoustic-Articulatory Feature Fusion For Dysarthric Speech Recognition. ICASSP Zhengjun Yue, Erfan Loweimi, Zoran Cvetkovic, Heidi Christensen, Jon Barker
2022	A	`conf`	RCT: Random consistency training for semi-supervised sound event detection. INTERSPEECH Nian Shao, Erfan Loweimi, Xiaofei Li
2022	Misc	`conf`	Raw Source and Filter Modelling for Dysarthric Speech Recognition. ICASSP Zhengjun Yue, Erfan Loweimi, Zoran Cvetkovic
2021	—	`conf`	On The Usefulness of Self-Attention for Automatic Speech Recognition with Transformers. SLT Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals
2021	A	`conf`	Speech Acoustic Modelling Using Raw Source and Filter Components. Interspeech Erfan Loweimi, Zoran Cvetkovic, Peter Bell, Steve Renals
2021	Misc	`conf`	Speech Acoustic Modelling from Raw Phase Spectrum. ICASSP Erfan Loweimi, Zoran Cvetkovic, Peter Bell, Steve Renals
2021	A	`conf`	Stochastic Attention Head Removal: A Simple and Effective Method for Improving Transformer Based ASR Models. Interspeech Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals
2021	Misc	`conf`	Train Your Classifier First: Cascade Neural Networks Training from Upper Layers to Lower Layers. ICASSP Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals
2021	J	`jnl`	Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers. CoRR Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals
2021	J	`jnl`	rct: random consistency training for semi-supervised sound event detection. CoRR Nian Shao, Erfan Loweimi, Xiaofei Li
2020	A	`conf`	On the Robustness and Training Dynamics of Raw Waveform Models. INTERSPEECH Erfan Loweimi, Peter Bell, Steve Renals
2020	J	`jnl`	On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers. CoRR Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals
2020	A	`conf`	Raw Sign and Magnitude Spectra for Multi-Head Acoustic Modelling. INTERSPEECH Erfan Loweimi, Peter Bell, Steve Renals
2020	J	`jnl`	Stochastic Attention Head Removal: A Simple and Effective Method for Improving Automatic Speech Recognition with Transformers. CoRR Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals
2020	J	`jnl`	When Can Self-Attention Be Replaced by Feed Forward Layers? CoRR Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals
2019	J	`jnl`	Acoustic Model Adaptation from Raw Waveforms with SincNet. CoRR Joachim Fainberg, Ondrej Klejch, Erfan Loweimi, Peter Bell, Steve Renals
2019	C	`conf`	Acoustic Model Adaptation from Raw Waveforms with Sincnet. ASRU Joachim Fainberg, Ondrej Klejch, Erfan Loweimi, Peter Bell, Steve Renals
2019	A	`conf`	Learning Temporal Clusters Using Capsule Routing for Speech Emotion Recognition. INTERSPEECH Md Asif Jalal, Erfan Loweimi, Roger K. Moore, Thomas Hain
2019	A	`conf`	On Learning Interpretable CNNs with Parametric Modulated Kernel-Based Filters. INTERSPEECH Erfan Loweimi, Peter Bell, Steve Renals
2019	Misc	`conf`	On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition. ICASSP Erfan Loweimi, Peter Bell, Steve Renals
2019	A	`conf`	Trainable Dynamic Subsampling for End-to-End Speech Recognition. INTERSPEECH Shucong Zhang, Erfan Loweimi, Yumo Xu, Peter Bell, Steve Renals
2019	Misc	`conf`	Windowed Attention Mechanisms for Speech Recognition. ICASSP Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals
2018	Misc	`conf`	Exploring the Use of Group Delay for Generalised VTS Based Noise Compensation. ICASSP Erfan Loweimi, Jon Barker, Thomas Hain
2018	A	`conf`	On the Usefulness of the Speech Phase Spectrum for Pitch Extraction. INTERSPEECH Erfan Loweimi, Jon Barker, Thomas Hain
2018	—	`—`	Robust phase-based speech signal processing from source-filter separation to model-based robust ASR. Erfan Loweimi
2017	A	`conf`	Channel Compensation in the Generalised Vector Taylor Series Approach to Robust ASR. INTERSPEECH Erfan Loweimi, Jon Barker, Thomas Hain
2017	A	`conf`	Robust Source-Filter Separation of Speech Signal in the Phase Domain. INTERSPEECH Erfan Loweimi, Jon Barker, Oscar Saz-Torralba, Thomas Hain
2017	Misc	`conf`	Statistical normalisation of phase-based feature representation for robust speech recognition. ICASSP Erfan Loweimi, Jon Barker, Thomas Hain
2016	A	`conf`	Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition. INTERSPEECH Erfan Loweimi, Jon Barker, Thomas Hain
2015	—	`conf`	Long-Term Statistical Feature Extraction from Speech Signal and Its Application in Emotion Recognition. SLSP Erfan Loweimi, Mortaza Doulaty, Jon Barker, Thomas Hain
2015	A	`conf`	Source-filter separation of speech signal in the phase domain. INTERSPEECH Erfan Loweimi, Jon Barker, Thomas Hain
2013	Misc	`conf`	A new phase-based feature representation for robust speech recognition. ICASSP Erfan Loweimi, Seyed Mohammad Ahadi, Thomas Drugman
2013	—	`conf`	On the Importance of Pre-emphasis and Window Shape in Phase-Based Speech Recognition. NOLISP Erfan Loweimi, Seyed Mohammad Ahadi, Thomas Drugman, Samira Loveymi
2011	A	`conf`	A new group delay-based feature for robust speech recognition. ICME Erfan Loweimi, Seyed Mohammad Ahadi
2011	A	`conf`	Phase-Only Speech Reconstruction Using Very Short Frames. INTERSPEECH Erfan Loweimi, Seyed Mohammad Ahadi, Hamid Sheikhzadeh
2010	—	`conf`	Objective evaluation of phase and magnitude only reconstructed speech: New considerations. ISSPA Erfan Loweimi, Seyed Mohammad Ahadi