Similar to humans' cognitive ability to generalize knowledge and skills, self-supervised
learning (SSL) targets discovering general representations from large-scale data. This …

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

Many self-supervised speech models, varying in their pre-training objective, input modality,
and pre-training data, have been proposed in the last few years. Despite impressive …

Speech processing Universal PERformance Benchmark (SUPERB) is a leaderboard to
benchmark the performance of Self-Supervised Learning (SSL) models on various speech …

Generative models have gained more and more attention in recent years for their
remarkable success in tasks that required estimating and sampling data distribution to …

Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-
world settings such as negotiation, medical diagnosis, and criminal investigation. It serves …

Speech representations learned from Self-supervised learning (SSL) models can benefit
various speech processing tasks. However, utilizing SSL representations usually requires …

We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised
speech representation for better performance, generalization, and efficiency. The challenge …

Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled
speech signals to reach impressive performance on speech tasks using only small amounts …

Self-Supervised Learning (SSL) from speech data has produced models that have achieved
remarkable performance in many tasks, and that are known to implicitly represent many …