activity
20002021
most citedDynamic Evaluation of Neural Sequence Models

60 citations · 170 across the 14 of their papers we have counts for

collaborators
Showing cs.CLShow all

15 papers · 1 filter

cs.CL20204 cited

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

Shucong Zhang, Erfan Loweimi, Peter Bell +1

Self-attention models such as Transformers, which can capture temporal relationships without being limited by the distance between events, have given competitive speech recognition…

cs.CL2020

Stochastic Attention Head Removal: A simple and effective method for improving Transformer Based ASR Models

Shucong Zhang, Erfan Loweimi, Peter Bell +1

Recently, Transformer based models have shown competitive automatic speech recognition (ASR) performance. One key factor in the success of these models is the multi-head attention…

cs.CL2020

European Language Grid: An Overview

Georg Rehm, Maria Berger, Ela Elsholz +33

With 24 official EU and many additional languages, multilingualism in Europe and an inclusive Digital Single Market can only be enabled through Language Technologies (LTs). Europea…

cs.CL2019

Multi-scale Octave Convolutions for Robust Speech Recognition

Joanna Rownicka, Peter Bell, Steve Renals

We propose a multi-scale octave convolution layer to learn robust speech representations efficiently. Octave convolutions were introduced by Chen et al [1] in the computer vision f…

cs.CL2019

Speaker Adaptive Training using Model Agnostic Meta-Learning

Ondřej Klejch, Joachim Fainberg, Peter Bell +1

Speaker adaptive training (SAT) of neural network acoustic models learns models in a way that makes them more suitable for adaptation to test conditions. Conventionally, model-base…

cs.CL2019

Embeddings for DNN speaker adaptive training

Joanna Rownicka, Peter Bell, Steve Renals

In this work, we investigate the use of embeddings for speaker-adaptive training of DNNs (DNN-SAT) focusing on a small amount of adaptation data per speaker. DNN-SAT can be viewed…