Transferring the knowledge of large language models (LLMs) is a promisin...
Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have ...
We introduce two techniques, length perturbation and n-best based label
...
This paper describes a novel knowledge distillation framework that lever...
We present a comprehensive study on building and adapting RNN transducer...
An essential component of spoken language understanding (SLU) is slot
fi...
With recent advances in deep learning, considerable attention has been g...
Conventional automatic speech recognition (ASR) systems trained from
fra...
Language models (LMs) based on Long Short Term Memory (LSTM) have shown ...
One of the most difficult speech recognition tasks is accurate recogniti...
Recurrent Neural Network (RNN) and one of its specific architectures, Lo...