As one of the important facilities for marine exploration, as well as environment monitoring, access control, and security, underwater wireless sensor networks (UWSNs) are widely used in related military and civil fields, since the sensor node localization is the basis of UWSNs’ application in various related fields. Therefore, the research of localization algorithms based on UWSNs has gradually become one of the research hotspots today. However, unlike terrestrial wireless sensor networks (WSNs), many terrestrial monitoring and localization technologies cannot be directly applied to the underwater environment. Moreover, due to the complexity and particularity of the underwater environment, the localization of underwater sensor nodes still faces challenges, such as the localization ratio of sensor nodes, time synchronization, localization accuracy, and the mobility of nodes. In this paper, we propose a mobility-assisted localization scheme with time synchronization-free feature (MALS-TSF) for three-dimensional (3D) large-scale UWSNs. In addition, the underwater drift of the sensor node is considered in this scheme. The localization scheme can be divided into two phases. In Phase I, anchor nodes are distributed in the monitoring area, reducing the monitoring cost. Then, we address a time-synchronization-free localization scheme, to obtain the coordinates of the unknown sensor nodes. In Phase II, we use the method of two-way TOA to locate the remaining ordinary sensor nodes. The simulation results show that MALS-TSF can achieve a relatively high localization ratio without time synchronization.
Convolutional neural networks (CNNs) are frequently employed in acoustic scene classification (ASC) tasks due to their ability to gather time-frequency information pertaining to the spectrum. However, the present research on ASC systems necessitates considering the model's complexity, which frequently results in an indistinct acquisition of time-frequency information within the confines of convolutional operations. This paper proposes a time-frequency pyramid pooling (TFPP) strategy that is based on low complexity for ASC, which is incorporated into the convolutional layer. The proposed TFPP strategy is utilized to acquire a local time-frequency information representation. This is achieved by employing a multi-scale pyramid computation performed on the two dimensions of the input feature map. Moreover, integrating multiple TFPP layers can facilitate the fusion effect of the time-frequency information derived from feature maps with varying resolutions. The experimental performance in three ASC databases shows the effectiveness of the proposed CNN-TFPP model in ASC tasks.
30 July 2025 in IEEE Transactions on Audio, Speech and Language Processing
Accurate evaluation of hearing aid speech quality is crucial for optimizing the auditory experience of hearing-impaired people. Aiming at the shortcomings of existing methods that rely on clean reference signals and do not take into account the effects of differences in Prescription Formula (PF), this paper proposes a non-intrusive speech quality evaluation framework based on speech label assistance, and multi-task learning strategy, termed MTSE-LA. The framework effectively mitigates evaluation bias caused by PF variations and effectively improves the prediction accuracy of speech quality metrics. MTSE-LA consists of three core modules: a feature extraction module, a label classification module, and a score prediction module. The feature extraction module extracts deep frame-level features from speech using a joint Convolutional Neural Network and Bidirectional Long Short-term Memory network (CNN-BiLSTM) model. The label classification module, acting as a pre-trained network, identifies PF labels and embeds them into the extracted frame-level features, which are then fed into the speech quality prediction branch of the multi-task score prediction module. Effective prediction of speech intelligibility is achieved by introducing the output vectors of the modulation filter bank to the speech intelligibility prediction branch to ensure synergy in the multi-task learning process. Moreover, each prediction branch uses the multi-head self-attention mechanism to capture contextual information and model the importance of speech frames. Experimental results demonstrate that MTSE-LA considerably improves the prediction accuracy of the Hearing Aid Speech Quality Index (HASQI) under multiple PF configurations and different degrees of hearing loss conditions. Compared with existing cutting-edge methods, the proposed framework exhibits higher correlation and fitting accuracy, establishing its reliability and superiority in the field of non-intrusive speech quality evaluation for hearing aids.
4 December 2023 in Multimedia Tools and Applications