Follow
Shucong Zhang
Shucong Zhang
Verified email at sms.ed.ac.uk - Homepage
Title
Cited by
Cited by
Year
On The Usefulness of Self-Attention for Automatic Speech Recognition with Transformers
S Zhang, E Loweimi, P Bell, S Renals
2021 IEEE Spoken Language Technology Workshop (SLT), 89-96, 2021
342021
Windowed attention mechanisms for speech recognition
S Zhang, E Loweimi, P Bell, S Renals
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
212019
Learning Noise Invariant Features Through Transfer Learning For Robust End-to-End Speech Recognition
S Zhang, CT Do, R Doddipatla, S Renals
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
162020
Stochastic Attention Head Removal: A Simple and Effective Method for Improving Automatic Speech Recognition with Transformers
S Zhang, E Loweimi, P Bell, S Renals
arXiv e-prints, arXiv: 2011.04004, 2020
11*2020
Trainable Dynamic Subsampling for End-to-End Speech Recognition.
S Zhang, E Loweimi, Y Xu, P Bell, S Renals
INTERSPEECH, 1413-1417, 2019
62019
Transformer-Based Streaming ASR with Cumulative Attention
M Li, S Zhang, C Zorilă, R Doddipatla
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
52022
On the (In) Efficiency of Acoustic Feature Extractors for Self-Supervised Speech Representation Learning
T Parcollet, S Zhang, R van Dalen, AGCP Ramos, S Bhattacharya
Interspeech 2023, 2023
42023
Cross-attention is all you need: Real-time streaming transformers for personalised speech enhancement
S Zhang, M Chadwick, AGCP Ramos, S Bhattacharya
arXiv preprint arXiv:2211.04346, 2022
32022
Sumformer: A Linear-Complexity Alternative to Self-Attention for Speech Recognition
T Parcollet, R van Dalen, S Zhang, S Bhattacharya
arXiv preprint arXiv:2307.07421, 2023
22023
Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
S Zhang, CT Do, R Doddipatla, E Loweimi, P Bell, S Renals
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
22021
Selective Adaptation of End-to-End Speech Recognition using Hybrid CTC/Attention Architecture for Noise Robustness
CT Do, S Zhang, T Hain
2020 28th European Signal Processing Conference (EUSIPCO), 321-325, 2021
22021
Real-Time Personalised Speech Enhancement Transformers with Dynamic Cross-attended Speaker Representations
S Zhang, M Chadwick, AGCP Ramos, T Parcollet, R van Dalen, ...
1*
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
T Parcollet, H Nguyen, S Evain, MZ Boito, A Pupier, S Mdhaffar, H Le, ...
arXiv preprint arXiv:2309.05472, 2023
2023
Top-down training for neural networks
S Zhang, CT Do, R Doddipatla, E Loweimi, P Bell, S Renals
2019
The system can't perform the operation now. Try again later.
Articles 1–14