Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

With the latest advances in deep learning-based generative models, it has not taken long to
take advantage of their remarkable performance in the area of time series. Deep neural …

Large-scale generative models such as GPT and DALL-E have revolutionized the research
community. These models not only generate high fidelity outputs, but are also generalists …

Speech neuroprostheses have the potential to restore communication to people living with
paralysis, but naturalistic speed and expressivity are elusive. Here we use high-density …

Recently, instruction-following audio-language models have received broad attention for
audio interaction with humans. However, the absence of pre-trained audio models capable …

We study the capabilities of speech processing systems trained simply to predict large
amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual …

The massive growth of self-supervised learning (SSL) has been witnessed in language,
vision, speech, and audio domains over the past few years. While discrete label prediction is …

In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …

This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-
supervised representation learning from audio spectrograms. Following the Transformer …

Self-supervised learning (SSL) achieves great success in speech recognition, while limited
exploration has been attempted for other speech processing tasks. As speech signal …