Related papers: On Compressing Sequences for Self-Supervised Speec…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature extractors or model initializers before fine-tuning. The former severely limits the…

Self-supervised features are typically used in place of filter-bank features in speaker verification models. However, these models were originally designed to ingest filter-bank features as inputs, and thus, training them on top of…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

The era of huge data necessitates highly efficient machine learning algorithms. Many common machine learning algorithms, however, rely on computationally intensive subroutines that are prohibitively expensive on large datasets. Oftentimes,…

This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their…

This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training. In particular, we deal with the localization…

Sustainable artificial intelligence focuses on data, hardware, and algorithms to make machine learning models more environmentally responsible. In particular, machine learning models for speech representations are computationally expensive,…

The slowness principle is a concept inspired by the visual cortex of the brain. It postulates that the underlying generative factors of a quickly varying sensory signal change on a slower time scale. Unsupervised learning of intermediate…

Auto-regressive models are widely used in sequence generation problems. The output sequence is typically generated in a predetermined order, one discrete unit (pixel or word or character) at a time. The models are trained by teacher-forcing…

Recently the focus of the computer vision community has shifted from expensive supervised learning towards self-supervised learning of visual representations. While the performance gap between supervised and self-supervised has been…

Self-supervised learning of convolutional neural networks can harness large amounts of cheap unlabeled data to train powerful feature representations. As surrogate task, we jointly address ordering of visual data in the spatial and temporal…

While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose…

Support Vector Machines (SVM), a popular machine learning technique, has been applied to a wide range of domains such as science, finance, and social networks for supervised learning. Whether it is identifying high-risk patients by…

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training…

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass…

Self-supervised learning has emerged as a method for utilizing massive unlabeled data for pre-training models, providing an effective feature extractor for various mobile sensing applications. However, when deployed to end-users, these…

Attention mechanism in sequence-to-sequence models is designed to model the alignments between acoustic features and output tokens in speech recognition. However, attention weights produced by models trained end to end do not always…