Related papers: SpikeVox: Towards Energy-Efficient Speech Therapy …
Speech enhancement (SE) improves communication in noisy environments, affecting areas such as automatic speech recognition, hearing aids, and telecommunications. With these domains typically being power-constrained and event-based while…
Spiking neural networks (SNNs) offer a promising avenue to implement deep neural networks in a more energy-efficient way. However, the network architectures of existing SNNs for language tasks are still simplistic and relatively shallow,…
As spiking neural networks receive more attention, we look toward applications of this computing paradigm in fields other than computer vision and signal processing. One major field, underexplored in the neuromorphic setting, is Natural…
Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large…
Spiking Neural Networks (SNNs) promise energy-efficient vision, but applying them to RGB visual tracking remains difficult: Existing SNN tracking frameworks either do not fully align with spike-driven computation or do not fully leverage…
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…
Spiking neural networks (SNNs) are posited as a computationally efficient and biologically plausible alternative to conventional neural architectures, with their core computational framework primarily using the leaky integrate-and-fire…
Spiking Neural Networks (SNNs) offer a biologically inspired computational paradigm, enabling energy-efficient data processing through spike-based information transmission. Despite notable advancements in hardware for SNNs, spike encoding…
Brain-computer interfaces (BCIs) promise to enable vital functions, such as speech and prosthetic control, for individuals with neuromotor impairments. Central to their success are neural decoders, models that map neural activity to…
Speech enhancement seeks to extract clean speech from noisy signals. Traditional deep learning methods face two challenges: efficiently using information in long speech sequences and high computational costs. To address these, we introduce…
Neuromorphic computing and spiking neural networks (SNNs) are gaining traction across various artificial intelligence (AI) tasks thanks to their potential for efficient energy usage and faster computation speed. This comparative advantage…
Spiking Neural Networks (SNNs) represent the latest generation of neural computation, offering a brain-inspired alternative to conventional Artificial Neural Networks (ANNs). Unlike ANNs, which depend on continuous-valued signals, SNNs…
Recent advancements in large language models (LLMs) with billions of parameters have improved performance in various applications, but their inference processes demand significant energy and computational resources. In contrast, the human…
Modern surgical systems increasingly rely on intelligent scene understanding to improve intra-operative safety and situational awareness, with surgical scene segmentation playing a fundamental role in fine-grained surgical perception.…
This paper presents a novel FPGA-based neuromorphic cochlea, leveraging the general-purpose spike-coding algorithm, Spiketrum. The focus of this study is on the development and characterization of this cochlea model, which excels in…
Transformer has obtained promising results on cognitive speech signal processing field, which is of interest in various applications ranging from emotion to neurocognitive disorder analysis. However, most works treat speech signal as a…
Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment in resource-constrained environments. Spiking Neural…
Application of deep convolutional spiking neural networks (SNNs) to artificial intelligence (AI) tasks has recently gained a lot of interest since SNNs are hardware-friendly and energy-efficient. Unlike the non-spiking counterparts, most of…
Speaker extraction aims to mimic humans' selective auditory attention by extracting a target speaker's voice from a multi-talker environment. It is common to perform the extraction in frequency-domain, and reconstruct the time-domain signal…
Generating spoken dialogue is inherently more complex than monologue text-to-speech (TTS), as it demands both realistic turn-taking and the maintenance of distinct speaker timbres. While existing autoregressive (AR) models have made…