End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty
recognizing uncommon words, that appear infrequently in the training data. One promising …

End-to-end (E2E) systems for automatic speech recognition (ASR), such as RNN
Transducer (RNN-T) and Listen-Attend-Spell (LAS) blend the individual components of a …

In this work, we exploit speech enhancement for improving a re-current neural network
transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent …

Contextual knowledge is important for real-world automatic speech recognition (ASR)
applications. In this paper, a novel tree-constrained pointer generator (TCPGen) component …

Incorporating biasing words obtained as contextual knowledge is critical for many automatic
speech recognition (ASR) applications. This paper proposes the use of graph neural …

Contextual knowledge is essential for reducing speech recognition errors on high-valued
long-tail words. This paper proposes a novel tree-constrained pointer generator (TCPGen) …

Current ASR systems are mainly trained and evaluated at the utterance level. Long range
cross utterance context can be incorporated. A key task is to derive a suitable compact …

In this work, to measure the accuracy and efficiency for a latency-controlled streaming
automatic speech recognition (ASR) application, we perform comprehensive evaluations on …

In this paper, a new two-step joint optimization approach based on the asynchronous
subregion optimization method is proposed for training a pipeline model composed of two …

Incorporating biasing words obtained through contextual knowledge is paramount in
automatic speech recognition (ASR) applications. This paper proposes an innovative …