17 citations · 60 across the 28 of their papers we have counts for
6 papers · 1 filter
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…
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…
Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines
David Wan, Zhengping Jiang, Chris Kedzie +3
In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation. ASR output segmentation is crucial, as ASR systems s…
Leveraging speaker attribute information using multi task learning for speaker verification and diarization
Chau Luu, Peter Bell, Steve Renals
Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between…
When Can Self-Attention Be Replaced by Feed Forward Layers?
Shucong Zhang, Erfan Loweimi, Peter Bell +1
Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outst…
DropClass and DropAdapt: Dropping classes for deep speaker representation learning
Chau Luu, Peter Bell, Steve Renals
Many recent works on deep speaker embeddings train their feature extraction networks on large classification tasks, distinguishing between all speakers in a training set. Empirical…