Language models (LMs) pre-trained on massive amounts of text, in particular bidirectional
encoder representations from Transformers (BERT), generative pre-training (GPT), and GPT …

End-to-end automatic speech recognition (ASR) and large language models, such as
Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite …

State-of-the-art neural network language models (NNLMs) represented by long short term
memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly …

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

Model adaptation is crucial to handle the discrepancy between proxy training data and
actual users' data received. To effectively perform adaptation, textual data of users is …

Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have been
successfully applied to ASR N-best rescoring. However, whether or how they can benefit …

Conformer transducer achieves new state-of-the-art end-to-end (E2E) system performance
and has become increasingly appealing for production. In this paper, we study how to …

State-of-the-art neural language models (LMs) represented by Transformers are highly
complex. Their use of fixed, deterministic parameter estimates fail to account for model …

Large language models (LLMs) have been successfully applied for rescoring automatic
speech recognition (ASR) hypotheses. However, their ability to rescore ASR hypotheses of …

Despite the recent advancements in test automation, testing often remains a manual, and
costly, activity in many industries. Manual test cases, often described only in natural …