Related papers: ATST: Audio Representation Learning with Teacher-S…

Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches.…

Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks, particularly those with a limited amount of data. However, the quality of SSL representations depends highly on the…

Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations like random crop and color jitter to achieve invariant…

Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions. In this work,…

Recently proposed consistency-based Semi-Supervised Learning (SSL) methods such as the $\Pi$-model, temporal ensembling, the mean teacher, or the virtual adversarial training, have advanced the state of the art in several SSL tasks. These…

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

Self-Supervised Learning (SSL) is an increasingly popular ML paradigm that trains models to transform complex inputs into representations without relying on explicit labels. These representations encode similarity structures that enable…

Performance in Speech Emotion Recognition (SER) on a single language has increased greatly in the last few years thanks to the use of deep learning techniques. However, cross-lingual SER remains a challenge in real-world applications due to…

The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they encounter the domain mismatch problem between pre-trained and…

The past few years have witnessed a remarkable advance in deep learning for EEG-based sleep stage classification (SSC). However, the success of these models is attributed to possessing a massive amount of labeled data for training, limiting…

Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data…

Self-supervised learning (SSL) has shown tremendous success in various speech-related downstream tasks, including Automatic Speech Recognition (ASR). The output embeddings of the SSL model are treated as powerful short-time representations…

Recently, wearable emotion recognition based on peripheral physiological signals has drawn massive attention due to its less invasive nature and its applicability in real-life scenarios. However, how to effectively fuse multimodal data…

Self-supervised learning (SSL) to learn high-level speech representations has been a popular approach to building Automatic Speech Recognition (ASR) systems in low-resource settings. However, the common assumption made in literature is that…

Automatic singing voice understanding tasks, such as singer identification, singing voice transcription, and singing technique classification, benefit from data-driven approaches that utilize deep learning techniques. These approaches work…

The problem of fully supervised classification is that it requires a tremendous amount of annotated data, however, in many datasets a large portion of data is unlabeled. To alleviate this problem semi-supervised learning (SSL) leverages the…

In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of…

Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets. Despite this, speech SSL representations may fail while…

Most semi-supervised learning (SSL) models entail complex structures and iterative training processes as well as face difficulties in interpreting their predictions to users. To address these issues, this paper proposes a new interpretable…

With the advances in deep learning, the performance of end-to-end (E2E) single-task models for speech and audio processing has been constantly improving. However, it is still challenging to build a general-purpose model with high…