Related papers: COALA: Co-Aligned Autoencoders for Learning Semant…
We show that a Modular Neural Network (MNN) can combine various speech enhancement modules, each of which is a Deep Neural Network (DNN) specialized on a particular enhancement job. Differently from an ordinary ensemble technique that…
It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…
We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds. The proposed DNN…
Representation learning plays a central role in structuring internal embeddings to capture the statistical properties of language, influencing the coherence and contextual consistency of generated text. Statistical Coherence Alignment is…
Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…
In the use of deep neural networks, it is crucial to provide appropriate input representations for the network to learn from. In this paper, we propose an approach to learn a representation that focus on rhythmic representation which is…
Deep representation learning offers a powerful paradigm for mapping input data onto an organized embedding space and is useful for many music information retrieval tasks. Two central methods for representation learning include deep metric…
While neural-based models have led to significant advancements in audio feature extraction, the interpretability of the learned representations remains a critical challenge. To address this, disentanglement techniques have been integrated…
We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple…
Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…
Deep neural networks (DNNs) used for brain-computer-interface (BCI) classification are commonly expected to learn general features when trained across a variety of contexts, such that these features could be fine-tuned to specific contexts.…
The deployment of machine listening algorithms in real-life applications is often impeded by a domain shift caused for instance by different microphone characteristics. In this paper, we propose a novel domain adaptation strategy based on…
Environmental audio tagging aims to predict only the presence or absence of certain acoustic events in the interested acoustic scene. In this paper we make contributions to audio tagging in two parts, respectively, acoustic modeling and…
Generative models capture the true distribution of data, yielding semantically rich representations. Denoising diffusion models (DDMs) exhibit superior generative capabilities, though efficient representation learning for them are lacking.…
Advancements in audio neural networks have established state-of-the-art results on downstream audio tasks. However, the black-box structure of these models makes it difficult to interpret the information encoded in their internal audio…
A lot of work has been done to build text-based language models for performing different NLP tasks, but not much research has been done in the case of audio-based language models. This paper proposes a Convolutional Autoencoder based neural…
We explore why deep convolutional neural networks (CNNs) with small two-dimensional kernels, primarily used for modeling spatial relations in images, are also effective in speech recognition. We analyze the representations learned by deep…
Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…
We propose the Neuralogram -- a deep neural network based representation for understanding audio signals which, as the name suggests, transforms an audio signal to a dense, compact representation based upon embeddings learned via a neural…
Methods for extracting audio and speech features have been studied since pioneering work on spectrum analysis decades ago. Recent efforts are guided by the ambition to develop general-purpose audio representations. For example, deep neural…