In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …

Transformers have recently dominated the ASR field. Although able to yield good
performance, they involve an autoregressive (AR) decoder to generate tokens one by one …

Non-autoregressive (NAR) generation, which is first proposed in neural machine translation
(NMT) to speed up inference, has attracted much attention in both machine learning and …

We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech
recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder …

We propose to deliberate the hypothesis alignment of a streaming RNN-T model with the
previously proposed Align-Refine non-autoregressive decoding method and its improved …

We propose a domain adaptation method that enables connectionist temporal classification
(CTC)-based end-to-end (E2E) automatic speech recognition (ASR) models to adapt to a …

Non-autoregressive (NAR) modeling has gained significant interest in speech processing
since these models achieve dramatically lower inference time than autoregressive (AR) …

We propose a fast and accurate end-to-end (E2E) model, which executes automatic speech
recognition (ASR) and downstream natural language processing (NLP) simultaneously. The …

There is often a trade-off between performance and latency in streaming automatic speech
recognition (ASR). Traditional methods such as look-ahead and chunk-based methods …

Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve
high accuracy and fast inference by simplifying the autoregressive (AR) generation process …