Related papers: Perceptual Loss Function for Neural Modelling of A…

Deep neural network models have become the dominant approach to a large variety of tasks within music information retrieval (MIR). These models generally require large amounts of (annotated) training data to achieve high accuracy. Because…

In applications that use emotion recognition via speech, frame-loss can be a severe issue given manifold applications, where the audio stream loses some data frames, for a variety of reasons like low bandwidth. In this contribution, we…

We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence…

Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant…

Channel pruning, which seeks to reduce the model size by removing redundant channels, is a popular solution for deep networks compression. Existing channel pruning methods usually conduct layer-wise channel selection by directly minimizing…

Robust loss functions are essential for training deep neural networks with better generalization power in the presence of noisy labels. Symmetric loss functions are confirmed to be robust to label noise. However, the symmetric condition is…

Single image super-resolution (SISR) is an ill-posed problem with an indeterminate number of valid solutions. Solving this problem with neural networks would require access to extensive experience, either presented as a large training set…

In recent years, limited research has discussed the loss function in the super-resolution process. The majority of those studies have only used perceptual similarity conventionally. This is while the development of appropriate loss can…

Accent conversion aims to convert the accent of a source speech to a target accent, meanwhile preserving the speaker's identity. This paper introduces a novel non-autoregressive framework for accent conversion that learns accent-agnostic…

Many audio applications rely on filter banks (FBs) to analyze, process, and re-synthesize sounds. To approximate the auditory frequency resolution in the signal chain, some applications rely on perceptually motivated FBs, the gammatone FB…

Estimating time-frequency domain masks for single-channel speech enhancement using deep learning methods has recently become a popular research field with promising results. In this paper, we propose a novel components loss (CL) for the…

Natural language processing (NLP) enables the understanding and generation of meaningful human language, typically using a pre-trained complex architecture on a large dataset to learn the language and next fine-tune its weights to implement…

Speech recognition in noisy and channel distorted scenarios is often challenging as the current acoustic modeling schemes are not adaptive to the changes in the signal distribution in the presence of noise. In this work, we develop a novel…

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…

Large pre-trained models, or foundation models, have shown impressive performance when adapted to a variety of downstream tasks, often out-performing specialized models. Hypernetworks, neural networks that generate some or all of the…

Representation learning is a key technique in modern machine learning that enables models to identify meaningful patterns in complex data. However, different methods tend to extract distinct aspects of the data, and relying on a single…

Accurately interpreting cardiac auscultation signals plays a crucial role in diagnosing and managing cardiovascular diseases. However, the paucity of labelled data inhibits classification models' training. Researchers have turned to…

Many super-resolution (SR) models are optimized for high performance only and therefore lack efficiency due to large model complexity. As large models are often not practical in real-world applications, we investigate and propose novel loss…

Web-scale pre-training datasets are the cornerstone of LLMs' success. However, text data curated from the Internet inevitably contains random noise caused by decoding errors or unregulated web content. In contrast to previous works that…

Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition. The same philosophy…