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 …

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 …

Transformer-based models have led to significant innovation in various classic and practical
subjects, including speech processing, natural language processing, and computer vision …

Recently, end-to-end models have been widely used in automatic speech recognition (ASR)
systems. Two of the most representative approaches are connectionist temporal …

Hotword customization is one of the concerned issues remained in ASR field-it is of value to
enable users of ASR systems to customize names of entities, persons and other phrases to …

Mixture-of-experts based models, which use language experts to extract language-specific
representations effectively, have been well applied in code-switching automatic speech …

Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end
approach. Unlike English where the writing system is closely related to sound, Chinese …

Contextualized end-to-end automatic speech recognition has been an active research area,
with recent efforts focusing on the implicit learning of contextual phrases based on the final …

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

Conventional ASR systems use frame-level phoneme posterior to conduct force-alignment
(FA) and provide timestamps, while end-to-end ASR systems especially AED based ones …