Related papers: Streaming Anchor Loss: Augmenting Supervision with…

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…

In contrast to the natural capabilities of humans to learn new tasks in a sequential fashion, neural networks are known to suffer from catastrophic forgetting, where the model's performances on old tasks drop dramatically after being…

Most recent self-supervised learning methods learn visual representation by contrasting different augmented views of images. Compared with supervised learning, more aggressive augmentations have been introduced to further improve the…

Transferring knowledge across many streaming processes remains an uncharted territory in the existing literature and features unique characteristics: no labelled instance of the target domain, covariate shift of source and target domain,…

Machine learning is being deployed in a growing number of applications which demand real-time, accurate, and robust predictions under heavy query load. However, most machine learning frameworks and systems only address model training and…

We investigate a monotonic multihead attention (MMA) by extending hard monotonic attention to Transformer-based automatic speech recognition (ASR) for online streaming applications. For streaming inference, all monotonic attention (MA)…

We introduce LIMES, a new method for learning with non-stationary streaming data, inspired by the recent success of meta-learning. The main idea is not to attempt to learn a single classifier that would have to work well across all…

Unsupervised domain adaption has proven to be an effective approach for alleviating the intensive workload of manual annotation by aligning the synthetic source-domain data and the real-world target-domain samples. Unfortunately, mapping…

We develop the first active learning method for contextual linear optimization. Specifically, we introduce a label acquisition algorithm that sequentially decides whether to request the ``labels'' of feature samples from an unlabeled data…

Estimating model accuracy on unseen, unlabeled datasets is crucial for real-world machine learning applications, especially under distribution shifts that can degrade performance. Existing methods often rely on predicted class probabilities…

We present a simple neural network model which combines a locally-connected feedforward structure, as is traditionally used to model inter-neuron connectivity, with a layer of undifferentiated connections which model the diffuse projections…

In recent years, with the rapid development of sensing technology and the Internet of Things (IoT), sensors play increasingly important roles in traffic control, medical monitoring, industrial production and etc. They generated high volume…

Recent advances in deep learning have pushed the performances of visual saliency models way further than it has ever been. Numerous models in the literature present new ways to design neural networks, to arrange gaze pattern data, or to…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Semantic segmentation is a key problem for many computer vision tasks. While approaches based on convolutional neural networks constantly break new records on different benchmarks, generalizing well to diverse testing environments remains a…

Training speech recognition systems on noisy transcripts is a significant challenge in industrial pipelines, where datasets are enormous and ensuring accurate transcription for every instance is difficult. In this work, we introduce novel…

Event-based camera has emerged as a promising paradigm for robot perception, offering advantages with high temporal resolution, high dynamic range, and robustness to motion blur. However, existing deep learning-based event processing…

The Dense Audio-Visual Event Localization (DAVEL) task aims to temporally localize events in untrimmed videos that occur simultaneously in both the audio and visual modalities. This paper explores DAVEL under a new and more challenging…

Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance…

The goal of this work is Active Speaker Detection (ASD), a task to determine whether a person is speaking or not in a series of video frames. Previous works have dealt with the task by exploring network architectures while learning…