Related papers: Multi-View Frequency-Attention Alternative to CNN …

In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) for complex spectral mapping based speech enhancement, and…

We introduce a novel neural network module that adeptly handles recursive data flow in neural network architectures. At its core, this module employs a self-consistent approach where a set of recursive equations is solved iteratively,…

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they…

A novel and efficient end-to-end learning model for automatic modulation classification is proposed for wireless spectrum monitoring applications, which automatically learns from the time domain in-phase and quadrature data without…

This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model…

Transformers are among the state of the art for many tasks in speech, vision, and natural language processing, among others. Self-attentions, which are crucial contributors to this performance have quadratic computational complexity, which…

Speech Emotion Recognition (SER) is crucial in human-machine interactions. Mainstream approaches utilize Convolutional Neural Networks or Recurrent Neural Networks to learn local energy feature representations of speech segments from speech…

The Dual-Path Convolution Recurrent Network (DPCRN) was proposed to effectively exploit time-frequency domain information. By combining the DPRNN module with Convolution Recurrent Network (CRN), the DPCRN obtained a promising performance in…

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we…

Automatic Modulation Classification (AMC) is a critical component in cognitive radio systems and spectrum management applications. This study presents a comprehensive comparative analysis of three attention mechanisms (i.e., baseline…

This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios. We present a comprehensive set of experiments comparing fixed…

Transformer has achieved extraordinary performance in Natural Language Processing and Computer Vision tasks thanks to its powerful self-attention mechanism, and its variant Conformer has become a state-of-the-art architecture in the field…

In this study, we propose the global context guided channel and time-frequency transformations to model the long-range, non-local time-frequency dependencies and channel variances in speaker representations. We use the global context…

Face attribute evaluation plays an important role in video surveillance and face analysis. Although methods based on convolution neural networks have made great progress, they inevitably only deal with one local neighborhood with…

Recent papers in neural machine translation have proposed the strict use of attention mechanisms over previous standards such as recurrent and convolutional neural networks (RNNs and CNNs). We propose that by running traditionally stacked…

Attention-based encoder-decoder, e.g. transformer and its variants, generates the output sequence in an autoregressive (AR) manner. Despite its superior performance, AR model is computationally inefficient as its generation requires as many…

Recurrent Neural Networks (RNNs) have long been the dominant architecture in sequence-to-sequence learning. RNNs, however, are inherently sequential models that do not allow parallelization of their computations. Transformers are emerging…

While recurrent neural networks still largely define state-of-the-art speech recognition systems, the Transformer network has been proven to be a competitive alternative, especially in the offline condition. Most studies with Transformers…

Region proposal based methods like R-CNN and Faster R-CNN models have proven to be extremely successful in object detection and segmentation tasks. Recently, Transformers have also gained popularity in the domain of Computer Vision, and are…

Despite significant efforts over the last few years to build a robust automatic speech recognition (ASR) system for different acoustic settings, the performance of the current state-of-the-art technologies significantly degrades in noisy…