相关论文: End-to-End Training Approaches for Discriminative …

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the…

Learning from label proportions (LLP) aims at learning an instance-level classifier with label proportions in grouped training data. Existing deep learning based LLP methods utilize end-to-end pipelines to obtain the proportional loss with…

Deep Metric Learning (DML) learns a non-linear semantic embedding from input data that brings similar pairs together while keeping dissimilar data away from each other. To this end, many different methods are proposed in the last decade…

End-to-end (E2E) neural models are increasingly attracting attention as a promising modeling approach for mispronunciation detection and diagnosis (MDD). Typically, these models are trained by optimizing a cross-entropy criterion, which…

Visual speech recognition models traditionally consist of two stages, feature extraction and classification. Several deep learning approaches have been recently presented aiming to replace the feature extraction stage by automatically…

Steering a car through traffic is a complex task that is difficult to cast into algorithms. Therefore, researchers turn to training artificial neural networks from front-facing camera data stream along with the associated steering angles.…

End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired…

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

Multi-task learning is a method for improving the generalizability of multiple tasks. In order to perform multiple classification tasks with one neural network model, the losses of each task should be combined. Previous studies have mostly…

In spoken language understanding (SLU), what the user says is converted to his/her intent. Recent work on end-to-end SLU has shown that accuracy can be improved via pre-training approaches. We revisit ideas presented by Lugosch et al. using…

The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multi-speaker speech recognition. However, up until now, state-of-the-art neural network-based time domain source…

Speech recognition is a sequence prediction problem. Besides employing various deep learning approaches for framelevel classification, sequence-level discriminative training has been proved to be indispensable to achieve the…

Trajectory sampling in the Frenet(road-aligned) frame, is one of the most popular methods for motion planning of autonomous vehicles. It operates by sampling a set of behavioural inputs, such as lane offset and forward speed, before solving…

ASR has been shown to achieve great performance recently. However, most of them rely on massive paired data, which is not feasible for low-resource languages worldwide. This paper investigates how to learn directly from unpaired phone…

The traditional communication model based on chain of multiple independent processing blocks is constraint to efficiency and introduces artificial barriers. Thus, each individually optimized block does not guarantee end-to-end performance…

The concept of learning to optimize involves utilizing a trainable optimization strategy rather than relying on manually defined full gradient estimations such as ADAM. We present a framework that jointly trains the full gradient estimator…

Large machine learning models trained on diverse data have recently seen unprecedented success. Federated learning enables training on private data that may otherwise be inaccessible, such as domain-specific datasets decentralized across…

Reinforcement Learning (RL) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. Typical RL methods optimize under an overall sequence reward, which can lead to a suboptimal learning process. This…

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused…