相关论文: Leveraging Deep Neural Network Activation Entropy …

Unseen data can degrade performance of deep neural net acoustic models. To cope with unseen data, adaptation techniques are deployed. For unlabeled unseen data, one must generate some hypothesis given an existing model, which is used as the…

Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is…

Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm. However, such a trained-well transformation is vulnerable to unseen noises that are not included in…

We introduce an unsupervised formulation to estimate heteroscedastic uncertainty in retrieval systems. We propose an extension to triplet loss that models data uncertainty for each input. Besides improving performance, our formulation…

Current speech deepfake detection approaches perform satisfactorily against known adversaries; however, generalization to unseen attacks remains an open challenge. The proliferation of speech deepfakes on social media underscores the need…

Unsupervised speech recognition is a task of training a speech recognition model with unpaired data. To determine when and how unsupervised speech recognition can succeed, and how classification error relates to candidate training…

The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Data augmentation is an inexpensive way to increase training data diversity and is commonly achieved via transformations of existing data. For tasks such as classification, there is a good case for learning representations of the data that…

Adapting pre-trained deep learning models to new and unknown environments remains a major challenge in underwater acoustic localization. We show that although the performance of pre-trained models suffers from mismatch between the training…

Unseen or out-of-domain data can seriously degrade the performance of a neural network model, indicating the model's failure to generalize to unseen data. Neural net pruning can not only help to reduce a model's size but can improve the…

Uncertainty estimation aims to evaluate the confidence of a trained deep neural network. However, existing uncertainty estimation approaches rely on low-dimensional distributional assumptions and thus suffer from the high dimensionality of…

Data augmentation (DA) has been widely used to improve the generalization of deep neural networks. While existing DA methods have proven effective, they often rely on augmentation operations with random magnitudes to each sample. However,…

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…

Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…

The principle of maximum entropy is a broadly applicable technique for computing a distribution with the least amount of information possible while constrained to match empirically estimated feature expectations. However, in many real-world…

Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the…

Unsupervised transfer learning-based change detection methods exploit the feature extraction capability of pre-trained networks to distinguish changed pixels from the unchanged ones. However, their performance may vary significantly…

In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with…

The majority of deep learning-based speech enhancement methods require paired clean-noisy speech data. Collecting such data at scale in real-world conditions is infeasible, which has led the community to rely on synthetically generated…