To train machine learning algorithms to predict emotional expressions in terms of arousal and valence, annotated datasets are needed. However, as different people perceive others' emotional expressions differently, their annotations are subjective. To account for this, annotations are typically collected from multiple annotators and averaged to obtain ground-truth labels. However, when exclusively trained on this averaged ground-truth, the model is agnostic to the inherent subjectivity in emotional expressions. In this work, we therefore propose an end-to-end Bayesian neural network capable of being trained on a distribution of annotations to also capture the subjectivity-based label uncertainty. Instead of a Gaussian, we model the annotation distribution using Student's t-distribution, which also accounts for the number of annotations available. We derive the corresponding Kullback-Leibler divergence loss and use it to train an estimator for the annotation distribution, from which the mean and uncertainty can be inferred. We validate the proposed method using two in-the-wild datasets. We show that the proposed t-distribution based approach achieves state-of-the-art uncertainty modeling results in speech emotion recognition, and also consistent results in cross-corpora evaluations. Furthermore, analyses reveal that the advantage of a t-distribution over a Gaussian grows with increasing inter-annotator correlation and a decreasing number of annotations available.

ND methods use noise or noisy speech enhancement using a dynamical variational autoencoder speech training samples to learn some noise characteristics. In (DVAE) as the clean speech model and non-negative matrix factorization contrast, NA methods only use clean speech signals for training (NMF) as the noise model. We propose to replace and the noise characteristics are estimated at test time for the NMF noise model with a deep dynamical generative model each noisy speech sequence to process. A typical unsupervised (DDGM) depending either on the DVAE latent variables, or on NA approach uses a pre-trained variational autoencoder (VAE) the noisy observations, or on both. This DDGM can be trained as a prior distribution of the clean speech signal and a nonnegative in three configurations: noise-agnostic, noise-dependent and matrix factorization (NMF) model for the noise variance noise adaptation after noise-dependent training.

Motivated by the recent success of Machine Learning (ML) tools in wireless communications, the idea of semantic communication by Weaver from 1949 has gained attention. It breaks with Shannon's classic design paradigm by aiming to transmit the meaning of a message, i.e., semantics, rather than its exact version and thus allows for savings in information rate. In this work, we extend the fundamental approach from Basu et al. for modeling semantics to the complete communications Markov chain. Thus, we model semantics by means of hidden random variables and define the semantic communication task as the data-reduced and reliable transmission of messages over a communication channel such that semantics is best preserved. We cast this task as an end-to-end Information Bottleneck problem, allowing for compression while preserving relevant information most. As a solution approach, we propose the ML-based semantic communication system SINFONY and use it for a distributed multipoint scenario: SINFONY communicates the meaning behind multiple messages that are observed at different senders to a single receiver for semantic recovery. We analyze SINFONY by processing images as message examples. Numerical results reveal a tremendous rate-normalized SNR shift up to 20 dB compared to classically designed communication systems.

Transformer is a deep neural network that employs a self-attention mechanism to comprehend the contextual relationships within sequential data. Unlike conventional neural networks or updated versions of Recurrent Neural Networks (RNNs) such as Long Short-Term Memory (LSTM), transformer models excel in handling long dependencies between input sequence elements and enable parallel processing. As a result, transformer-based models have attracted substantial interest among researchers in the field of artificial intelligence. This can be attributed to their immense potential and remarkable achievements, not only in Natural Language Processing (NLP) tasks but also in a wide range of domains, including computer vision, audio and speech processing, healthcare, and the Internet of Things (IoT). Although several survey papers have been published highlighting the transformer's contributions in specific fields, architectural differences, or performance evaluations, there is still a significant absence of a comprehensive survey paper encompassing its major applications across various domains. Therefore, we undertook the task of filling this gap by conducting an extensive survey of proposed transformer models from 2017 to 2022. Our survey encompasses the identification of the top five application domains for transformer-based models, namely: NLP, Computer Vision, Multi-Modality, Audio and Speech Processing, and Signal Processing. We analyze the impact of highly influential transformer-based models in these domains and subsequently classify them based on their respective tasks using a proposed taxonomy. Our aim is to shed light on the existing potential and future possibilities of transformers for enthusiastic researchers, thus contributing to the broader understanding of this groundbreaking technology.

When using machine learning for fault detection, a common problem is the fact that most data sets are very unbalanced, with the minority class (a fault) being the interesting one. In this paper, we investigate the usage of Venn-Abers predictors, looking specifically at the effect on the minority class predictions. A key property of Venn-Abers predictors is that they output well-calibrated probability intervals. In the experiments, we apply Venn-Abers calibration to decision trees, random forests and XGBoost models, showing how both overconfident and underconfident models are corrected. In addition, the benefit of using the valid probability intervals produced by Venn-Abers for decision support is demonstrated. When using techniques producing opaque underlying models, e.g., random forest and XGBoost, each prediction will consist of not only the label, but also a valid probability interval, where the width is an indication of the confidence in the estimate. Adding Venn-Abers on top of a decision tree allows inspection and analysis of the model, to understand both the underlying relationship, and finding out in which parts of feature space that the model is accurate and/or confident.

Current speech enhancement (SE) research has largely neglected channel attention and spatial attention, and encoder-decoder architecture-based networks have not adequately considered how to provide efficient inputs to the intermediate enhancement layer. To address these issues, this paper proposes a time-frequency (T-F) domain SE network (DPCFCS-Net) that incorporates improved densely connected blocks, dual-path modules, convolution-augmented transformers (conformers), channel attention, and spatial attention. Compared with previous models, our proposed model has a more efficient encoder-decoder and can learn comprehensive features. Experimental results on the VCTK+DEMAND dataset demonstrate that our method outperforms existing techniques in SE performance. Furthermore, the improved densely connected block and two dimensions attention module developed in this work are highly adaptable and easily integrated into existing networks.

Minimizing response times is crucial for emergency medical services to reduce patients' waiting times and to increase their survival rates. Many models exist to optimize operational tasks such as ambulance allocation and dispatching. Including accurate demand forecasts in such models can improve operational decision-making. Against this background, we present a novel convolutional neural network (CNN) architecture that transforms time series data into heatmaps to predict ambulance demand. Applying such predictions requires incorporating external features that influence ambulance demands. We contribute to the existing literature by providing a flexible, generic CNN architecture, allowing for the inclusion of external features with varying dimensions. Additionally, we provide a feature selection and hyperparameter optimization framework utilizing Bayesian optimization. We integrate historical ambulance demand and external information such as weather, events, holidays, and time. To show the superiority of the developed CNN architecture over existing approaches, we conduct a case study for Seattle's 911 call data and include external information. We show that the developed CNN architecture outperforms existing state-of-the-art methods and industry practice by more than 9%.

Logic synthesis is the first and most vital step in chip design. This steps converts a chip specification written in a hardware description language (such as Verilog) into an optimized implementation using Boolean logic gates. State-of-the-art logic synthesis algorithms have a large number of logic minimization heuristics, typically applied sequentially based on human experience and intuition. The choice of the order greatly impacts the quality (e.g., area and delay) of the synthesized circuit. In this paper, we propose INVICTUS, a model-based offline reinforcement learning (RL) solution that automatically generates a sequence of logic minimization heuristics ("synthesis recipe") based on a training dataset of previously seen designs. A key challenge is that new designs can range from being very similar to past designs (e.g., adders and multipliers) to being completely novel (e.g., new processor instructions). %Compared to prior work, INVICTUS is the first solution that uses a mix of RL and search methods joint with an online out-of-distribution detector to generate synthesis recipes over a wide range of benchmarks. Our results demonstrate significant improvement in area-delay product (ADP) of synthesized circuits with up to 30\% improvement over state-of-the-art techniques. Moreover, INVICTUS achieves up to $6.3\times$ runtime reduction (iso-ADP) compared to the state-of-the-art.

We propose a unified approach to obtain structured sparse optimal paths in the latent space of a variational autoencoder (VAE) using dynamic programming and Gumbel propagation. We solve the classical optimal path problem by a probability softening solution, called the stochastic optimal path, and transform a wide range of DP problems into directed acyclic graphs in which all possible paths follow a Gibbs distribution. We show the equivalence of the Gibbs distribution to a message-passing algorithm by the properties of the Gumbel distribution and give all the ingredients required for variational Bayesian inference. Our approach obtaining latent optimal paths enables end-to-end training for generative tasks in which models rely on the information of unobserved structural features. We validate the behavior of our approach and showcase its applicability in two real-world applications: text-to-speech and singing voice synthesis.

Therefore, it is essential to enhance End-to-end automatic speech recognition (ASR) and large language the performance of these models on such domain-specific models, such as Whisper and GPT-2, have recently been words without sacrificing their capacity for generalisation, and scaled to use vast amounts of training data. Despite the large contextual biasing is one possible solution. Contextual biasing amount of training data, infrequent content words that occur in aims to incorporate contextual knowledge into end-to-end ASR a particular task may still exhibit poor ASR performance, with systems. Contextual knowledge is often represented as a biasing contextual biasing a possible remedy. This paper investigates list, comprising words that carry important information and the effectiveness of neural contextual biasing for Whisper combined are essential to downstream tasks, such as restaurant names in with GPT-2. Specifically, this paper proposes integrating an ontology for a task-oriented dialogue system. The inclusion an adapted tree-constrained pointer generator (TCPGen) component of these words in the biasing list has been shown to significantly for Whisper and a dedicated training scheme to dynamically improve recognition performance.