The papers in this special section focus on distributed signal processing for edge learning (EL). EL is a new and promising technology for implementing artificial intelligence (AI) algorithms at edge devices over wireless networks.
Recently, self-supervised learning (SSL) from unlabelled speech data has gained increased attention in the automatic speech recognition (ASR) community. Typical SSL methods include autoregressive predictive coding (APC), Wav2vec2.0, and hidden unit BERT (HuBERT). However, SSL models are biased to the pretraining data. When SSL models are finetuned with data from another domain, domain shifting occurs and might cause limited knowledge transfer for downstream tasks.
Speech self-supervised learning has attracted much attention due to its promising performance in multiple downstream tasks, and has become a new growth engine for speech recognition in low-resource languages. In this paper, we exploit and analyze a series of wav2vec pre-trained models for speech recognition in 15 low-resource languages in the OpenASR21 Challenge.
Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains.
Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains.
The papers in this special section focus on self-supervised learning for speech and audio processing. A current trend in the machine learning community is the adoption of self-supervised approaches to pretrain deep networks. Self-supervised learning utilizes proxy-supervised learning tasks (or pretext tasks) - for example, distinguishing parts of the input signal from distractors or reconstructing masked input segments conditioned on unmasked segments—to obtain training data from unlabeled corpora.
Edge networks offer a promising solution for satisfying the increasing energy and computation needs of user devices with new data intensive services. A mutil-access edge computing (MEC) system with collocated MEC servers and base-stations/access points (BS/AP) has the ability to support multiple users for both data computation and wireless charging. We propose an integrated solution for wireless charging with computation offloading to satisfy the largest feasible proportion of requested wireless charging while keeping the total energy consumption at the minimum, subject to the MEC-AP transmit power and latency constraints.
This paper investigates an intelligent reflecting surface (IRS) assisted simultaneous wireless information and power transfer (SWIPT) system. Multiple IRSs deployed on unmanned aerial vehicles (UAVs) and ground building are considered in the proposed system for enhancing transmission of information and energy simultaneously. The optimization problem is formulated to maximize the average achievable rate over N time slots by jointly optimizing power splitting (PS) ratio, transmit beamforming, phase shifts and trajectories of UAVs.
The papers in this special section focuses on signal processing advances in wireless transmission of power and information. Wireless power transfer (WPT) and wireless information and power transfer (WIPT) have received growing attention in the research community in the past few years. In this special issue, a total of fourteen papers present state-of-the-art results in the broad area of wireless transmission of information and power with a special emphasis on signal processing advances.
Automotive imaging radars require high angular resolution which can be achieved by a large antenna aperture. In order to obey Nyquist spatial sampling rate, a large number of array elements and receive channels is required. In practice, this solution results in a prohibitively high cost and complexity.
@ieeeSPS
11.3K subscribers‧180 videos
