Related papers: Full Attention Bidirectional Deep Learning Structu…

Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range…

In this study, we propose a novel multi-modal end-to-end neural approach for automated assessment of non-native English speakers' spontaneous speech using attention fusion. The pipeline employs Bi-directional Recurrent Convolutional Neural…

Long-form speech recognition is an application area of increasing research focus. ASR models based on multi-head attention (MHA) are ill-suited to long-form ASR because of their quadratic complexity in sequence length. We build on recent…

The attention mechanism has become a cornerstone of modern deep learning architectures, where keys and values are typically derived from the same underlying sequence or representation. This work explores a less conventional scenario, when…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by…

FullSubNet is our recently proposed real-time single-channel speech enhancement network that achieves outstanding performance on the Deep Noise Suppression (DNS) Challenge dataset. A number of variants of FullSubNet have been proposed, but…

In latest years, deep learning has gained a leading role in the pansharpening of multiresolution images. Given the lack of ground truth data, most deep learning-based methods carry out supervised training in a reduced-resolution domain.…

With new sequence models like Mamba and xLSTM, several studies have shown that these models match or outperform the state-of-the-art in single-channel speech enhancement and audio representation learning. However, prior research has…

A sequence-to-sequence model is a neural network module for mapping two sequences of different lengths. The sequence-to-sequence model has three core modules: encoder, decoder, and attention. Attention is the bridge that connects the…

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…

Voice controlled virtual assistants (VAs) are now available in smartphones, cars, and standalone devices in homes. In most cases, the user needs to first "wake-up" the VA by saying a particular word/phrase every time he or she wants the VA…

The most recent deep neural network (DNN) models exhibit impressive denoising performance in the time-frequency (T-F) magnitude domain. However, the phase is also a critical component of the speech signal that is easily overlooked. In this…

Although deep learning (DL) has achieved notable progress in speech enhancement (SE), further research is still required for a DL-based SE system to adapt effectively and efficiently to particular speakers. In this study, we propose a novel…

Applying neural-networks on Question Answering has gained increasing popularity in recent years. In this paper, I implemented a model with Bi-directional attention flow layer, connected with a Multi-layer LSTM encoder, connected with one…

Speech enhancement and source localization has been active research for several decades with a wide range of real-world applications. Recently, the Deep Complex Convolution Recurrent network (DCCRN) has yielded impressive enhancement…

Recent works have shown that Deep Recurrent Neural Networks using the LSTM architecture can achieve strong single-channel speech enhancement by estimating time-frequency masks. However, these models do not naturally generalize to…

For a speech-enhancement algorithm, it is highly desirable to simultaneously improve perceptual quality and recognition rate. Thanks to computational costs and model complexities, it is challenging to train a model that effectively…

Deep learning based single-channel speech enhancement tries to train a neural network model for the prediction of clean speech signal. There are a variety of popular network structures for single-channel speech enhancement, such as TCNN,…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…