相关论文: Memristive Nanowire Network for Energy Efficient A…

Recently, research on audio foundation models has witnessed notable advances, as illustrated by the ever improving results on complex downstream tasks. Subsequently, those pretrained networks have quickly been used for various audio…

Memristive devices present a promising foundation for next-generation information processing by combining memory and computation within a single physical substrate. This unique characteristic enables efficient, fast, and adaptive computing,…

The choice of neural network features can have a large impact on both the accuracy and speed of the network. Despite the current industry shift towards large transformer models, specialized binary classifiers remain critical for numerous…

Neuromorphic systems that learn and predict from streaming inputs hold significant promise in pervasive edge computing and its applications. In this paper, a neuromorphic system that processes spatio-temporal information on the edge is…

The development of memristive device technologies has reached a level of maturity to enable the design of complex and large-scale hybrid memristive-CMOS neural processing systems. These systems offer promising solutions for implementing…

Neuromorphic systems, inspired by the complexity and functionality of the human brain, have gained interest in academic and industrial attention due to their unparalleled potential across a wide range of applications. While their…

Deep neural networks have been demonstrated impressive results in various cognitive tasks such as object detection and image classification. In order to execute large networks, Von Neumann computers store the large number of weight…

Deep learning has celebrated resounding successes in many application areas of relevance to the Internet of Things (IoT), such as computer vision and machine listening. These technologies must ultimately be brought directly to the edge to…

Neuromorphic computing is poised to further the success of software-based neural networks by utilizing improved customized hardware. However, the translation of neuromorphic algorithms to hardware specifications is a problem that has been…

Current audio deepfake detection has achieved remarkable performance using diverse deep learning architectures such as ResNet, and has seen further improvements with the introduction of large models (LMs) like Wav2Vec. The success of large…

Speech emotion recognition systems have high prediction latency because of the high computational requirements for deep learning models and low generalizability mainly because of the poor reliability of emotional measurements across…

Noise suppression and speech distortion are two important aspects to be balanced when designing multi-channel Speech Enhancement (SE) algorithms. Although neural network models have achieved state-of-the-art noise suppression, their…

Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…

There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave…

Significant efforts are being invested to bring state-of-the-art classification and recognition to edge devices with extreme resource constraints (memory, speed, and lack of GPU support). Here, we demonstrate the first deep network for…

We introduce a time-domain framework for efficient multichannel speech enhancement, emphasizing low latency and computational efficiency. This framework incorporates two compact deep neural networks (DNNs) surrounding a multichannel neural…

Automatic speech recognition systems usually rely on spectral-based features, such as MFCC of PLP. These features are extracted based on prior knowledge such as, speech perception or/and speech production. Recently, convolutional neural…

We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via ad hoc…

Background: Active noise cancellation has been a subject of research for decades. Traditional techniques, like the Fast Fourier Transform, have limitations in certain scenarios. This research explores the use of deep neural networks (DNNs)…

Objective: Voice disorders significantly compromise individuals' ability to speak in their daily lives. Without early diagnosis and treatment, these disorders may deteriorate drastically. Thus, automatic classification systems at home are…