Related papers: SALADnet: Self-Attentive multisource Localization …

Recent advances in self-supervised learning (SSL) on Transformers have significantly improved speaker verification (SV) by providing domain-general speech representations. However, existing approaches have underutilized the multi-layered…

Retentive Network (RetNet) represents a significant advancement in neural network architecture, offering an efficient alternative to the Transformer. While Transformers rely on self-attention to model dependencies, they suffer from high…

Neural multi-channel speech enhancement models, in particular those based on the U-Net architecture, demonstrate promising performance and generalization potential. These models typically encode input channels independently, and integrate…

Existing approaches for replay and synthetic speech detection still lack generalizability to unseen spoofing attacks. This work proposes to leverage a novel model structure, so-called Res2Net, to improve the anti-spoofing countermeasure's…

Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, their expressive power and performance can be boosted by using…

3D speech enhancement can effectively improve the auditory experience and plays a crucial role in augmented reality technology. However, traditional convolutional-based speech enhancement methods have limitations in extracting dynamic voice…

Transformers have emerged as viable alternatives to convolutional neural networks owing to their ability to learn non-local region relationships in the spatial domain. The self-attention mechanism of the transformer enables transformers to…

Transformer-based end-to-end neural speaker diarization (EEND) models utilize the multi-head self-attention (SA) mechanism to enable accurate speaker label prediction in overlapped speech regions. In this study, to enhance the training…

This paper introduces an area-based source separation method designed for virtual meeting scenarios. The aim is to preserve speech signals from an unspecified number of sources within a defined spatial area in front of a linear microphone…

Self-attention has emerged as a core component of modern neural architectures, yet its theoretical underpinnings remain elusive. In this paper, we study self-attention through the lens of interacting entities, ranging from agents in…

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past…

State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs). FCNs rely on cascaded convolutional and pooling layers to gradually enlarge the receptive fields of neurons, resulting in an…

Closed-Set speaker identification aims to assign a speech utterance to one of a predefined set of enrolled speakers and requires robust modeling of speaker-specific characteristics across multiple temporal scales. While recent deep learning…

Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation…

We introduce SANDesc, a Streamlined Attention-Based Network for Descriptor extraction that aims to improve on existing architectures for keypoint description. Our descriptor network learns to compute descriptors that improve matching…

Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…

For dual-channel speech enhancement, it is a promising idea to design an end-to-end model based on the traditional array signal processing guideline and the manifold space of multi-channel signals. We found that the idea above can be…

Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outstanding performance of self-attention models is their ability…