Related papers: FFC-SE: Fast Fourier Convolution for Speech Enhanc…

In sound event detection (SED), convolutional neural networks (CNNs) are widely employed to extract time-frequency (TF) patterns from spectrograms. However, the ability of CNNs to recognize different sound events is limited by their…

The wide deployment of speech-based biometric systems usually demands high-performance speaker recognition algorithms. However, most of the prior works for speaker recognition either process the speech in the frequency domain or time…

We examine the performance profile of Convolutional Neural Network training on the current generation of NVIDIA Graphics Processing Units. We introduce two new Fast Fourier Transform convolution implementations: one based on NVIDIA's cuFFT…

Convolutional neural networks have become an essential element of spatial deep learning systems. In the prevailing architecture, the convolution operation is performed with Fast Fourier Transforms (FFT) electronically in GPUs. The…

Convolutional neural networks (CNNs) have a large number of variables and hence suffer from a complexity problem for their implementation. Different methods and techniques have developed to alleviate the problem of CNN's complexity, such as…

Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of these new techniques operate directly in the the short-time…

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones. A recent trend in speech and speaker recognition consists in discovering these representations starting from raw…

Deep learning has dramatically improved the performance of speech recognition systems through learning hierarchies of features optimized for the task at hand. However, true end-to-end learning, where features are learned directly from…

We propose a novel framework, termed Fourier-Activated Adapter (FAA), for parameter-efficient fine-tuning of large pre-trained language models. By incorporating random Fourier features into lightweight adapter modules, FAA decomposes…

The architecture of a neural network and the selection of its activation function are both fundamental to its performance. Equally vital is ensuring these two elements are well-matched, as their alignment is key to achieving effective…

Deep neural network solutions have emerged as a new and powerful paradigm for speech enhancement (SE). The capabilities to capture long context and extract multi-scale patterns are crucial to design effective SE networks. Such capabilities,…

Orthogonal frequency-division multiplexing (OFDM) has been selected as a baseline waveform for long-term evolution (LTE) and fifth-generation new radio (5G NR). Fast-convolution (FC)-based frequency-domain signal processing has been…

Speaker recognition using i-vector has been replaced by speaker recognition using deep learning. Speaker recognition based on Convolutional Neural Networks (CNNs) has been widely used in recent years, which learn low-level speech…

Current speech enhancement (SE) research has largely neglected channel attention and spatial attention, and encoder-decoder architecture-based networks have not adequately considered how to provide efficient inputs to the intermediate…

Facial Expression Recognition (FER) is vital for understanding interpersonal communication. However, existing classification methods often face challenges such as vulnerability to noise, imbalanced datasets, overfitting, and generalization…

Orthogonal frequency-division multiplexing (OFDM) has been selected as the basis for the fifth-generation new radio (5G-NR) waveform developments. However, effective signal processing tools are needed for enhancing the OFDM spectrum in…

Binaural speech enhancement faces a severe trade-off challenge, where state-of-the-art performance is achieved by computationally intensive architectures, while lightweight solutions often come at the cost of significant performance…

The SepFormer architecture shows very good results in speech separation. Like other learned-encoder models, it uses short frames, as they have been shown to obtain better performance in these cases. This results in a large number of frames…

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,…