相关论文: Ultra-Lightweight Speech Separation via Group Comm…

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…

Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic information. Most existing…

Predicting group behavior, how individuals coordinate, communicate, and interact during collaborative tasks, is essential for designing systems that can support team performance through real-time prediction and realistic simulation of…

Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with…

We study few-shot Natural Language Understanding (NLU) tasks with Large Language Models (LLMs) in federated learning (FL) scenarios. It is a challenging task due to limited labeled data and communication capacities in FL, especially with…

Speech separation on hearable devices can enable transformative augmented and enhanced hearing capabilities. However, state-of-the-art speech separation networks cannot run in real-time on tiny, low-power neural accelerators designed for…

This study introduces an ensemble framework for unstructured text categorization using large language models (LLMs). By integrating multiple models, the ensemble large language model (eLLM) framework addresses common weaknesses of…

The growing complexity of network traffic and demand for ultra-low latency communication require smarter packet traffic management. Existing Deep Learning-based queuing approaches struggle with dynamic network scenarios and demand high…

Foundation models for medical imaging demonstrate superior generalization capabilities across diverse anatomical structures and clinical applications. Their outstanding performance relies on substantial computational resources, limiting…

Deep learning methods have brought substantial advancements in speech separation (SS). Nevertheless, it remains challenging to deploy deep-learning-based models on edge devices. Thus, identifying an effective way to compress these large…

While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose…

Identification of the type of communication technology and/or modulation scheme based on detected radio signal are challenging problems encountered in a variety of applications including spectrum allocation and radio interference…

While Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks, their substantial computational requirements and restricted number of calls constrain their practical utility, especially in…

In this paper, we apply a latent class model (LCM) to the task of speaker diarization. LCM is similar to Patrick Kenny's variational Bayes (VB) method in that it uses soft information and avoids premature hard decisions in its iterations.…

Recently, federated large language models (LLMs) have drawn significant attention thanks to coupled capabilities of LLMs and federated learning (FL) that address privacy concerns in collaborative fine-tuning. However, due to large-scale…

Large Language Model (LLM) agents increasingly serve as personal assistants and workplace collaborators, where their utility depends on memory systems that extract, retrieve, and apply information across long-running conversations. However,…

The surge in connected devices in 6G with typical complex tasks requiring multi-user cooperation, such as smart agriculture and smart cities, poses significant challenges to unsustainable traditional communication. Fortunately, the booming…

In this paper, we propose a novel strategy for text-independent speaker identification system: Multi-Label Training (MLT). Instead of the commonly used one-to-one correspondence between the speech and the speaker label, we divide all the…

Collaborative learning across heterogeneous model architectures presents significant challenges in ensuring interoperability and preserving privacy. We propose a communication-efficient distributed learning framework that supports model…

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a…