SPS Feed

Spatial-angular separable convolution (SAS-conv) has been widely used for efficient and effective 4D light field (LF) feature embedding in different tasks, which mimics a 4D convolution by alternatively operating on 2D spatial slices and 2D angular slices. In this paper, we argue that, despite its global intensity modeling capabilities, SAS-conv can only embed local geometry information into the features, resulting in inferior performances in the regions with textures and occlusions. Because the epipolar lines are highly related to the scene depth, we introduce the concept of spatial-angular correlated convolution (SAC-conv).

This paper introduces a new framework for non-parallel emotion conversion in speech. Our framework is based on two key contributions. First, we propose a stochastic version of the popular Cycle-GAN model. Our modified loss function introduces a Kullback–Leibler (KL) divergence term that aligns the source and target data distributions learned by the generators, thus overcoming the limitations of sample-wise generation. By using a variational approximation to this stochastic loss function, we show that our KL divergence term can be implemented via a paired density discriminator.

Emotional voice conversion (VC) aims to convert a neutral voice to an emotional one while retaining the linguistic information and speaker identity. We note that the decoupling of emotional features from other speech information (such as content, speaker identity, etc.) is the key to achieving promising performance. Some recent attempts of speech representation decoupling on the neutral speech cannot work well on the emotional speech, due to the more complex entanglement of acoustic properties in the latter. 

A key challenge of image splicing detection is how to localize integral tampered regions without false alarm. Although current forgery detection approaches have achieved promising performance, the integrality and false alarm are overlooked. In this paper, we argue that the insufficient use of splicing boundary is a main reason for poor accuracy. To tackle this problem, we propose an Edge-enhanced Transformer (ET) for tampered region localization. Specifically, to capture rich tampering traces, a two-branch edge-aware transformer is built to integrate the splicing edge clues into the forgery localization network, generating forgery features and edge features.

Active reconfigurable intelligent surfaces (RISs) are a novel and promising technology that allows controlling the radio propagation environment while compensating for the product path loss along the RIS-assisted path. In this letter, we consider the classical radar detection problem and propose to use an active RIS to get a second independent look at a prospective target illuminated by the radar transmitter.

The algorithms based on the technique of optimal k -thresholding (OT) were recently proposed for signal recovery, and they are very different from the traditional family of hard thresholding methods. However, the computational cost for OT-based algorithms remains high at the current stage of their development. This stimulates the development of the so-called natural thresholding (NT) algorithm and its variants in this paper. The family of NT algorithms is developed through the first-order approximation of the so-called regularized optimal k -thresholding model, and thus the computational cost for this family of algorithms is significantly lower than that of the OT-based algorithms. 

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.

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.