More recently, Bidirectional Encoder Representations from Transformers (BERT) was
proposed and has achieved impressive success on many natural language processing …

We explore two adaptation approaches of deep Transformer based neural language models
(LMs) for automatic speech recognition. The first approach is a pretrain-finetune framework …

We propose two adaptation models for recurrent neural network language models
(RNNLMs) to capture topic effects and longdistance triggers for conversational automatic …

Although Long-Short Term Memory (LSTM) networks and deep Transformers are now
extensively used in offline ASR, it is unclear how best offline systems can be adapted to …

LSTM based language models are an important part of modern LVCSR systems as they
significantly improve performance over traditional backoff language models. Incorporating …

The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates
an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) …

Air Navigation Service Providers (ANSPs) replace paper flight strips through different digital
solutions. The instructed commands from an air traffic controller (ATCos) are then available …

Increasing digitization and automation is a widely accepted method to cope with the
challenges of constantly increasing air traffic. The analogue communication of air traffic …

Recurrent Neural Networks, in particular Long-Short TermMemory (LSTM) networks, are
widely used in AutomaticSpeech Recognition for language modelling during decoding …

Abstract Automatic Speech Recognition (ASR) has recently proved to be a useful tool to
reduce the workload of air traffic controllers leading to significant gains in operational …