Speech emotion recognition (SER) is a challenging task in human–computer interaction (HCI) systems. One of the key challenges in speech emotion recognition is to extract the emotional features effectively from a speech utterance. Despite the promising results of recent studies, they generally do not leverage advanced fusion algorithms for the generation of effective representations of emotional features in speech utterances. To address this problem, we describe the fusion of spatial and temporal feature representations of speech emotion by parallelizing convolutional neural networks (CNNs) and a Transformer encoder for SER. We stack two parallel CNNs for spatial feature representation in parallel to a Transformer encoder for temporal feature representation, thereby simultaneously expanding the filter depth and reducing the feature map with an expressive hierarchical feature representation at a lower computational cost. We use the RAVDESS dataset to recognize eight different speech emotions. We augment and intensify the variations in the dataset to minimize model overfitting. Additive White Gaussian Noise (AWGN) is used to augment the RAVDESS dataset. With the spatial and sequential feature representations of CNNs and the Transformer, the SER model achieves 82.31% accuracy for eight emotions on a hold-out dataset. In addition, the SER system is evaluated with the IEMOCAP dataset and achieves 79.42% recognition accuracy for five emotions. Experimental results on the RAVDESS and IEMOCAP datasets show the success of the presented SER system and demonstrate an absolute performance improvement over the state-of-the-art (SOTA) models.

The majority of the Earth’s surface is covered by water, with oceans holding approximately 97% of this water and serving as the lifeblood of our planet. These oceans are essential for various purposes, including transportation, sustenance, and communication. However, establishing effective communication networks between the numerous sub-islands present in many parts of the world poses significant challenges. Underwater optical wireless communication, or UWOC, can indeed be an excellent solution to provide seamless connectivity underwater. UWOC holds immense significance due to its ability to transmit data at high rates, low latency, and enhanced security. In this work, we propose polarization division multiplexing-based UWOC system under the impact of salinity with an on–off keying (OOK) modulation format. The proposed system aims to establish high-speed network connectivity between underwater divers/submarines in oceans at different salinity levels. The numerical simulation results demonstrate the effectiveness of our proposed system with a 2 Gbps data rate up to 10.5 m range in freshwater and up to 1.8 m in oceanic waters with salinity up to 35 ppt. Successful transmission of high-speed data is reported in underwater optical wireless communication, especially where salinity impact is higher.

Because of their simple design structure, end-to-end deep learning (E2E-DL) models have gained a lot of attention for speech enhancement. A number of DL models have achieved excellent results in eliminating the background noise and enhancing the quality as well as the intelligibility of noisy speech. Designing resource-efficient and compact models during real-time processing is still a key challenge. In order to enhance the accomplishment of E2E models, the sequential and local characteristics of speech signal should be efficiently taken into consideration while modeling. In this paper, we present resource-efficient and compact neural models for end-to-end noise-robust waveform-based speech enhancement. Combining the Convolutional Encode-Decoder (CED) and Recurrent Neural Networks (RNNs) in the Convolutional Recurrent Network (CRN) framework, we have aimed at different speech enhancement systems. Different noise types and speakers are used to train and test the proposed models. With LibriSpeech and the DEMAND dataset, the experiments show that the proposed models lead to improved quality and intelligibility with fewer trainable parameters, notably reduced model complexity, and inference time than existing recurrent and convolutional models. The quality and intelligibility are improved by 31.61% and 17.18% over the noisy speech. We further performed cross corpus analysis to demonstrate the generalization of the proposed E2E SE models across different speech datasets.

The ultra-wideband (UWB)-based real-time localization system (RTLS) is a promising technology for locating and tracking assets and personnel in real-time within a defined indoor environment since it provides high-ranging accuracy. However, its performance can be affected by the underlying antenna delays of UWB nodes, which act as a source of error during range estimations. Usually, measurement of the antenna delays is performed separately as a dedicated standalone procedure. Such an additional measurement procedure makes the UWB-based RTLS more tedious with manual interventions. Moreover, the air-time occupancy during the transmission and reception of signaling messages for range estimations between UWB node pairs also limits the serviceable capability of these networks. In this regard, we present a novel simultaneous ranging scheme that requires limited air-time occupancy during range estimations between UWB node pairs and also compensates for the error from the antenna delays. This paper provides a detailed mathematical modeling, system design, and implementation procedure of the proposed scheme. The effectiveness of the proposed scheme for locating a mobile node in an indoor environment is validated through experimental analysis. The results show that, compared to the state-of-the-art two-way ranging (TWR) method, the proposed scheme eliminates the requirement of dedicated standalone antenna delay measurement procedures of the nodes, increases air efficiency through the provision of simultaneous ranging, and provides relative root-mean-square errors (RMSEs) improvement for range and position estimations of approximately $54.52\%$ and $39.96\%$, respectively.