In this paper, we investigate the use of large language models (LLMs) li...
Reinforcement learning based dialogue policies are typically trained in
...
We introduce a monaural neural speaker embeddings extractor that compute...
This paper proposes a self-regularised minimum latency training (SR-MLT)...
This paper presents the use of non-autoregressive (NAR) approaches for j...
This paper proposes a new approach to perform unsupervised fine-tuning a...
Improving the accuracy of single-channel automatic speech recognition (A...
In this paper, we explore an improved framework to train a monoaural neu...
A major bottleneck for building statistical spoken dialogue systems for ...
In this paper, we propose an online attention mechanism, known as cumula...
Models that can handle a wide range of speakers and acoustic conditions ...
Impressive progress in neural network-based single-channel speech source...
A user input to a schema-driven dialogue information navigation system, ...
In this paper, we introduce a novel semi-supervised learning framework f...
This paper proposes an adaptation method for end-to-end speech recogniti...
Although the lower layers of a deep neural network learn features which ...
In this paper, we present a novel multi-channel speech extraction system...
This paper introduces a new method for multi-channel time domain speech
...
Utterance interpretation is one of the main functions of a dialogue mana...
Despite the strong modeling power of neural network acoustic models, spe...
The University of Sheffield (USFD) participated in the International Wor...