Recently, end-to-end sequence-to-sequence models for speech recognition have gained
significant interest in the research community. While previous architecture choices revolve …

Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have
been proposed to perform online speech recognition with linear-time decoding complexity …

Phones and their context-dependent variants have been the standard modeling units for
conventional speech recognition systems, while characters and subwords have …

Conventional automatic speech recognition (ASR) systems trained from frame-level
alignments can easily leverage posterior fusion to improve ASR accuracy and build a better …

In this work, we propose minimum Bayes risk (MBR) training of RNN-Transducer (RNN-T) for
end-to-end speech recognition. Specifically, initialized with a RNN-T trained model, MBR …

Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are
simpler to train, and more efficient to decode with, than sub-word systems. However, A2W …

Prior work has shown that connectionist temporal classification (CTC)-based automatic
speech recognition systems perform well when using bidirectional long short-term memory …

In this paper, we propose a refined multi-stage multi-task training strategy to improve the
performance of onli ne attention-based encoder-decoder (AED) models. A three-stage …

Non-native speech causes automatic speech recognition systems to degrade in
performance. Past strategies to address this challenge have considered model adaptation …

We present a novel training approach for connectionist temporal classification (CTC)-based
automatic speech recognition (ASR) systems. CTC models are promising for building both a …