Related papers: Gaussian-smoothed Imbalance Data Improves Speech E…

Advancements in spoken language processing have driven the development of spoken language models (SLMs), designed to achieve universal audio understanding by jointly learning text and audio representations for a wide range of tasks.…

Depression commonly co-occurs with neurodegenerative disorders like Multiple Sclerosis (MS), yet the potential of speech-based Artificial Intelligence for detecting depression in such contexts remains unexplored. This study examines the…

Diffusion models achieve remarkable generation quality, yet face a fundamental challenge known as memorization, where generated samples can replicate training samples exactly. We develop a theoretical framework to explain this phenomenon by…

Automatic speech emotion recognition (SER) is a challenging task that plays a crucial role in natural human-computer interaction. One of the main challenges in SER is data scarcity, i.e., insufficient amounts of carefully labeled data to…

In Speech Emotion Recognition (SER), emotional characteristics often appear in diverse forms of energy patterns in spectrograms. Typical attention neural network classifiers of SER are usually optimized on a fixed attention granularity. In…

Automatic Emotion Detection (ED) aims to build systems to identify users' emotions automatically. This field has the potential to enhance HCI, creating an individualised experience for the user. However, ED systems tend to perform poorly on…

Speech emotion recognition has evolved from research to practical applications. Previous studies of emotion recognition from speech have focused on developing models on certain datasets like IEMOCAP. The lack of data in the domain of…

Speech is the most common way humans express their feelings, and sentiment analysis is the use of tools such as natural language processing and computational algorithms to identify the polarity of these feelings. Even though this field has…

While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose…

Diffusion models generate high-quality synthetic data. They operate by defining a continuous-time forward process which gradually adds Gaussian noise to data until fully corrupted. The corresponding reverse process progressively "denoises"…

State-space models are successfully used in many areas of science, engineering and economics to model time series and dynamical systems. We present a fully Bayesian approach to inference \emph{and learning} (i.e. state estimation and system…

In emotion recognition, it is difficult to recognize human's emotional states using just a single modality. Besides, the annotation of physiological emotional data is particularly expensive. These two aspects make the building of effective…

Learning dynamical systems from incomplete or noisy data is inherently ill-posed, as a single observation may correspond to multiple plausible futures. While physics-based ensemble forecasting relies on perturbing initial states to capture…

Although current Text-To-Speech (TTS) models are able to generate high-quality speech samples, there are still challenges in developing emotion intensity controllable TTS. Most existing TTS models achieve emotion intensity control by…

Gaussian smoothing (GS) is a derivative-free optimization (DFO) algorithm that estimates the gradient of an objective using perturbations of the current parameters sampled from a standard normal distribution. We generalize it to sampling…

Emotion recognition in multi-speaker conversations faces significant challenges due to speaker ambiguity and severe class imbalance. We propose a novel framework that addresses these issues through three key innovations: (1) a speaker…

Speech Emotion Recognition (SER) is crucial for human-computer interaction but still remains a challenging problem because of two major obstacles: data scarcity and imbalance. Many datasets for SER are substantially imbalanced, where data…

Before entering the neural network, a token is generally converted to the corresponding one-hot representation, which is a discrete distribution of the vocabulary. Smoothed representation is the probability of candidate tokens obtained from…

The data scarcity problem in emotion recognition from electroencephalography (EEG) leads to difficulty in building an affective model with high accuracy using machine learning algorithms or deep neural networks. Inspired by emerging deep…

This paper proposes a new Bayesian strategy for the smooth estimation of altimetric parameters. The altimetric signal is assumed to be corrupted by a thermal and speckle noise distributed according to an independent and non identically…