Related papers: End-to-End Multi-Channel Transformer for Speech Re…

Transformer-based architectures for speaker verification typically require more training data than ECAPA-TDNN. Therefore, recent work has generally been trained on VoxCeleb1&2. We propose a backbone network based on self-attention, which…

Time series forecasting is a crucial challenge with significant applications in areas such as weather prediction, stock market analysis, and scientific simulations. This paper introduces an embedded decomposed transformer, 'EDformer', for…

Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is perceptually…

Large-scale sound recognition data sets typically consist of acoustic recordings obtained from multimedia libraries. As a consequence, modalities other than audio can often be exploited to improve the outputs of models designed for…

Transformer hugely benefits from its key design of the multi-head self-attention network (SAN), which extracts information from various perspectives through transforming the given input into different subspaces. However, its simple linear…

Transformer has become ubiquitous in the deep learning field. One of the key ingredients that destined its success is the self-attention mechanism, which allows fully-connected contextual encoding over input tokens. However, despite its…

With its strong modeling capacity that comes from a multi-head and multi-layer structure, Transformer is a very powerful model for learning a sequential representation and has been successfully applied to speech separation recently.…

Voice-controlled house-hold devices, like Amazon Echo or Google Home, face the problem of performing speech recognition of device-directed speech in the presence of interfering background speech, i.e., background noise and interfering…

This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain the multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for the design of attention networks by…

In recent years, transformer-based methods have achieved remarkable progress in medical image segmentation due to their superior ability to capture long-range dependencies. However, these methods typically suffer from two major limitations.…

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

Transformers have been extensively studied in medical image segmentation to build pairwise long-range dependence. Yet, relatively limited well-annotated medical image data makes transformers struggle to extract diverse global features,…

Emotion recognition from speech is a challenging task. Re-cent advances in deep learning have led bi-directional recur-rent neural network (Bi-RNN) and attention mechanism as astandard method for speech emotion recognition, extractingand…

Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer's quadratic complexity with respect to the input sequence length…

Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of patches consisting of split images. However, for complex…

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…

Automatic recognition systems for child speech are lagging behind those dedicated to adult speech in the race of performance. This phenomenon is due to the high acoustic and linguistic variability present in child speech caused by their…

Transformers have become the dominant architecture for sequence modeling tasks such as natural language processing or audio processing, and they are now even considered for tasks that are not naturally sequential such as image…

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

This paper proposes a novel automatic speech recognition (ASR) framework called Integrated Source-Channel and Attention (ISCA) that combines the advantages of traditional systems based on the noisy source-channel model (SC) and end-to-end…