Recent studies on software tool manipulation with large language models
...
While the general idea of self-supervised learning is identical across
m...
As the computational requirements for machine learning systems and the s...
This paper presents XLS-R, a large-scale model for cross-lingual speech
...
In this paper, we study training of automatic speech recognition system ...
Recent progress in self-training, self-supervised pretraining and
unsupe...
In this paper, we introduce the Kaizen framework that uses a continuousl...
Without positional information, attention-based transformer neural netwo...
Self-supervised learning of speech representations has been a very activ...
This paper introduces Multilingual LibriSpeech (MLS) dataset, a large
mu...
Is pushing numbers on a single benchmark valuable in automatic speech
re...
Recent results in end-to-end ASR have demonstrated the efficacy of simpl...
Self-training and unsupervised pre-training have emerged as effective
ap...
One of the main challenges for end-to-end speech translation is data
sca...
Pseudo-labeling has recently shown promise in end-to-end automatic speec...
We design an online end-to-end speech recognition system based on Time-D...
We introduce a new collection of spoken English audio suitable for train...
We study ResNet-, Time-Depth Separable ConvNets-, and Transformer-based
...
We propose a fully convolutional sequence-to-sequence encoder architectu...
This paper introduces wav2letter++, the fastest open-source deep learnin...
Current state-of-the-art speech recognition systems build on recurrent n...
Evaluating generative adversarial networks (GANs) is inherently challeng...
The growing explosion in the use of surveillance cameras in public secur...