相关论文: A consolidated view of loss functions for supervis…

Advanced auditory models are useful in designing signal-processing algorithms for hearing-loss compensation or speech enhancement. Such auditory models provide rich and detailed descriptions of the auditory pathway, and might allow for…

Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images. While L1 and L2 losses are perhaps the most widely used functions for this purpose, they do not necessarily lead…

We study the role of magnitude structured pruning as an architecture search to speed up the inference time of a deep noise suppression (DNS) model. While deep learning approaches have been remarkably successful in enhancing audio quality,…

The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which training and test…

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the…

The decoupling-style concept begins to ignite in the speech enhancement area, which decouples the original complex spectrum estimation task into multiple easier sub-tasks i.e., magnitude-only recovery and the residual complex spectrum…

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process,…

Feature mapping using deep neural networks is an effective approach for single-channel speech enhancement. Noisy features are transformed to the enhanced ones through a mapping network and the mean square errors between the enhanced and…

We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the…

The mean squared error (MSE) is a ubiquitous loss function for speech enhancement, but its problem is that the error cannot reflect the auditory perception quality. This is because MSE causes models to over-emphasize low-frequency…

For the convolutional neural network (CNN) used for pattern classification, the training loss function is usually applied to the final output of the network, except for some regularization constraints on the network parameters. However,…

This paper proposes neural networks for compensating sensorineural hearing loss. The aim of the hearing loss compensation task is to transform a speech signal to increase speech intelligibility after further processing by a person with a…

Comparing spoken segments is a central operation to speech processing. Traditional approaches in this area have favored frame-level dynamic programming algorithms, such as dynamic time warping, because they require no supervision, but they…

This paper studies the Speech Enhancement based on Deep Neural Networks. The proposed architecture gradually follows the signal transformation during enhancement by means of a visualization probe at each network block. Alongside the…

Deep learning has recently demonstrated its excellent performance on the task of multi-view stereo (MVS). However, loss functions applied for deep MVS are rarely studied. In this paper, we first analyze existing loss functions' properties…

Deep learning algorithm are increasingly used for speech enhancement (SE). In supervised methods, global and local information is required for accurate spectral mapping. A key restriction is often poor capture of key contextual information.…

All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that…

Representation learning methods have revolutionized machine learning on networks by converting discrete network structures into continuous domains. However, dynamic networks that evolve over time pose new challenges. To address this,…

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…

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…