As one of the most popular sequence-to-sequence modeling approaches for
...
The recently proposed conformer architecture has been successfully used ...
To improve the performance of state-of-the-art automatic speech recognit...
Sequence discriminative training is a great tool to improve the performa...
Attention-based encoder-decoder (AED) models learn an implicit internal
...
Acoustic modeling of raw waveform and learning feature extractors as par...
We present our transducer model on Librispeech. We study variants to inc...
Sequence-to-sequence models with an implicit alignment mechanism (e.g.
a...
We present a complete training pipeline to build a state-of-the-art hybr...
Sequence discriminative training criteria have long been a standard tool...
We present state-of-the-art automatic speech recognition (ASR) systems
e...