Automatic speech recognition research focuses on training and evaluating...
We present the SUPERB challenge at SLT 2022, which aims at learning
self...
This document describes version 0.10 of torchaudio: building blocks for
...
We propose a dynamic encoder transducer (DET) for on-device speech
recog...
Word Error Rate (WER) has been the predominant metric used to evaluate t...
In this work, to measure the accuracy and efficiency for a latency-contr...
There is a growing interest in the speech community in developing Recurr...
Attention-based models have been gaining popularity recently for their s...
In this paper, we summarize the application of transformer and its strea...
This paper proposes an efficient memory transformer Emformer for low lat...
Transformers, originally proposed for natural language processing (NLP)
...
Transformer-based acoustic modeling has achieved great suc-cess for both...
As one of the major sources in speech variability, accents have posed a ...
Neural transducer-based systems such as RNN Transducers (RNN-T) for auto...
We explore options to use Transformer networks in neural transducer for
...
In this paper, we propose a domain adversarial training (DAT) algorithm ...
This paper explores the use of adversarial examples in training speech
r...