Related papers: Hybrid Real- And Complex-Valued Neural Network Con…

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be…

Network binarization is a promising hardware-aware direction for creating efficient deep models. Despite its memory and computational advantages, reducing the accuracy gap between binary models and their real-valued counterparts remains an…

Despite noise suppression being a mature area in signal processing, it remains highly dependent on fine tuning of estimator algorithms and parameters. In this paper, we demonstrate a hybrid DSP/deep learning approach to noise suppression. A…

In recent years, deep learning has gained an indisputable success in computer vision, speech recognition, and natural language processing. After its rising success on these challenging areas, it has been studied on recommender systems as…

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

Although convolutional neural network (CNN) has made great progress, large redundant parameters restrict its deployment on embedded devices, especially mobile devices. The recent compression works are focused on real-value convolutional…

Recent progress in deep learning-based models has improved photo-realistic (or perceptual) single-image super-resolution significantly. However, despite their powerful performance, many methods are difficult to apply to real-world…

This paper explores the integration of model-based and data-driven approaches within the realm of neural speech and audio coding systems. It highlights the challenges posed by the subjective evaluation processes of speech and audio codecs…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

Speech enhancement plays an essential role in improving the quality of speech signals in noisy environments. This paper investigates the efficacy of integrating Bidirectional Gated Recurrent Units (BGRU) and Transformer models for speech…

This invention addresses fixed-point representations of convolutional neural networks (CNN) in integrated circuits. When quantizing a CNN for a practical implementation there is a trade-off between the precision used for operations between…

In this paper, we present ECAPA2, a novel hybrid neural network architecture and training strategy to produce robust speaker embeddings. Most speaker verification models are based on either the 1D- or 2D-convolutional operation, often…

Signal-dependent beamformers are advantageous over signal-independent beamformers when the acoustic scenario - be it real-world or simulated - is straightforward in terms of the number of sound sources, the ambient sound field and their…

Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs…

In this paper, we propose an end-to-end speech recognition network based on Nvidia's previous QuartzNet model. We try to promote the model performance, and design three components: (1) Multi-Resolution Convolution Module, replaces the…

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

In speech enhancement (SE), phase estimation is important for perceptual quality, so many methods take clean speech's complex short-time Fourier transform (STFT) spectrum or the complex ideal ratio mask (cIRM) as the learning target. To…

Magnetic resonance image reconstruction starting from undersampled k-space data requires the recovery of many potential nonlinear features, which is very difficult for algorithms to recover these features. In recent years, the development…

This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Residual Network. This is supported on single dimensional…

Speech enhancement can potentially benefit from the visual information from the target speaker, such as lip movement and facial expressions, because the visual aspect of speech is essentially unaffected by acoustic environment. In this…