Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

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 …

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 …

This paper proposes a method to relax the conditional independence assumption of
connectionist temporal classification (CTC)-based automatic speech recognition (ASR) …

Non-autoregressive (NAR) models simultaneously generate multiple outputs in a sequence,
which significantly reduces the inference speed at the cost of accuracy drop compared to …

This paper describes the recent development of ESPnet (https://github. com/espnet/espnet),
an end-to-end speech processing toolkit. This project was initiated in December 2017 to …

This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that
adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the …

In this study, we present recent developments of models trained with the RNN-T loss in
ESPnet. It involves the use of various archi-tectures such as recently proposed Conformer …

While Transformers have achieved promising results in end-to-end (E2E) automatic speech
recognition (ASR), their autoregressive (AR) structure becomes a bottleneck for speeding up …

Transformer 作为一种新的深度学习算法框架, 得到了越来越多研究人员的关注,
成为目前的研究热点. Transformer 模型中的自注意力机制受人类只关注于重要事物的启发 …