相关论文: Dynamic curriculum learning via data parameters fo…

Modern end-to-end speech recognition models show astonishing results in transcribing audio signals into written text. However, conventional data feeding pipelines may be sub-optimal for low-resource speech recognition, which still remains a…

Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance. Motivated by our insights from implicit curriculum…

Building efficient architecture in neural speech processing is paramount to success in keyword spotting deployment. However, it is very challenging for lightweight models to achieve noise robustness with concise neural operations. In a…

The performance of automatic speech recognition systems under noisy environments still leaves room for improvement. Speech enhancement or feature enhancement techniques for increasing noise robustness of these systems usually add components…

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of…

The expanding feature set of modern headphones puts a challenge on the design of their control interface. Users may want to separately control each feature or quickly switch between modes that activate different features. Traditional…

Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The…

Existing dialogue datasets contain lots of noise in their state annotations. Such noise can hurt model training and ultimately lead to poor generalization performance. A general framework named ASSIST has recently been proposed to train…

Curriculum learning techniques are a viable solution for improving the accuracy of automatic models, by replacing the traditional random training with an easy-to-hard strategy. However, the standard curriculum methodology does not…

Recent advances in speech deepfake detection (SDD) have significantly improved artifacts-based detection in spoofed speech. However, most models overlook speech naturalness, a crucial cue for distinguishing bona fide speech from spoofed…

Uncertainty estimation for unlabeled data is crucial to active learning. With a deep neural network employed as the backbone model, the data selection process is highly challenging due to the potential over-confidence of the model…

Event-based sensors offer significant advantages over traditional frame-based cameras, especially in scenarios involving rapid motion or challenging lighting conditions. However, event data frequently suffers from considerable noise,…

This study introduces a method to design a curriculum for machine-learning to maximize the efficiency during the training process of deep neural networks (DNNs) for speech emotion recognition. Previous studies in other machine-learning…

Label-noise or curated unlabeled data is used to compensate for the assumption of clean labeled data in training the conditional generative adversarial network; however, satisfying such an extended assumption is occasionally laborious or…

Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…

Pre-trained language models have achieved noticeable performance on the intent detection task. However, due to assigning an identical weight to each sample, they suffer from the overfitting of simple samples and the failure to learn complex…

We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private. The framework is based on active learning algorithms that are statistical in the…

In several studies, hybrid neural networks have proven to be more robust against noisy input data compared to plain data driven neural networks. We consider the task of estimating parameters of a mechanical vehicle model based on…

We propose self-training with noisy student-teacher approach for streaming keyword spotting, that can utilize large-scale unlabeled data and aggressive data augmentation. The proposed method applies aggressive data augmentation (spectral…

An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of…