相关论文: Hybrid Real- And Complex-Valued Neural Network Con…

Neuromorphic (brain-inspired) photonics leverages photonic chips to accelerate artificial intelligence, offering high-speed and energy efficient solutions in RF communication, tensor processing, and data classification. However, the limited…

Nearly all previous work on neural machine translation (NMT) has used quite restricted vocabularies, perhaps with a subsequent method to patch in unknown words. This paper presents a novel word-character solution to achieving open…

Complicated and deep neural network models can achieve high accuracy for image recognition. However, they require a huge amount of computations and model parameters, which are not suitable for mobile and embedded devices. Therefore,…

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…

Reconstructing the room transfer functions needed to calculate the complex sound field in a room has several important real-world applications. However, an unpractical number of microphones is often required. Recently, in addition to…

Deep neural networks have proven to be particularly effective in visual and audio recognition tasks. Existing models tend to be computationally expensive and memory intensive, however, and so methods for hardware-oriented approximation have…

Quality and intelligibility of speech signals are degraded under additive background noise which is a critical problem for hearing aid and cochlear implant users. Motivated to address this problem, we propose a novel speech enhancement…

Memory-augmented neural networks enhance a neural network with an external key-value memory whose complexity is typically dominated by the number of support vectors in the key memory. We propose a generalized key-value memory that decouples…

We develop hybrid memory architectures for general-purpose sequence processing neural networks, that combine key-value memory using softmax attention (KV-memory) with fast weight memory through dynamic synaptic modulation (FW-memory) -- the…

In hearing aids, the presence of babble noise degrades hearing intelligibility of human speech greatly. However, removing the babble without creating artifacts in human speech is a challenging task in a low SNR environment. Here, we sought…

This research explores a hybrid approach to fine-tuning large language models (LLMs) by integrating real-world and synthetic data to boost model performance, particularly in generating accurate and contextually relevant responses. By…

Recurrent neural networks have been widely used in sequence learning tasks. In previous studies, the performance of the model has always been improved by either wider or deeper structures. However, the former becomes more prone to…

Driven by the appealing properties of neural fields for storing and communicating 3D data, the problem of directly processing them to address tasks such as classification and part segmentation has emerged and has been investigated in recent…

Usually, complex-valued RKHS are presented as an straightforward application of the real-valued case. In this paper we prove that this procedure yields a limited solution for regression. We show that another kernel, here denoted as pseudo…

The research explores the potential of quantum deep learning models to address challenging machine learning problems that classical deep learning models find difficult to tackle. We introduce a novel model architecture that combines…

The dialogue management is a task of conversational artificial intelligence. The goal of the dialogue manager is to select the appropriate response to the conversational partner conditioned by the input message and recent dialogue state.…

We present scalable hybrid-parallel algorithms for training large-scale 3D convolutional neural networks. Deep learning-based emerging scientific workflows often require model training with large, high-dimensional samples, which can make…

Neural network based approaches to speech enhancement have shown to be particularly powerful, being able to leverage a data-driven approach to result in a significant performance gain versus other approaches. Such approaches are reliant on…

Speech recognition in noisy and channel distorted scenarios is often challenging as the current acoustic modeling schemes are not adaptive to the changes in the signal distribution in the presence of noise. In this work, we develop a novel…

The first artificial quantum neuron models followed a similar path to classic models, as they work only with discrete values. Here we introduce an algorithm that generalizes the binary model manipulating the phase of complex numbers. We…