相关论文: Rethinking the Separation Layers in Speech Separat…

Multi-channel speech separation in dynamic environments is challenging as time-varying spatial and spectral features evolve at different temporal scales. Existing methods typically employ sequential architectures, forcing a single network…

Semantic communication has emerged as a transformative paradigm in next-generation communication systems, leveraging advanced artificial intelligence (AI) models to extract and transmit semantic representations for efficient information…

Stacked intelligent metasurfaces (SIMs), which integrate multiple programmable metasurface layers, have recently emerged as a promising technology for advanced wave-domain signal processing. SIMs benefit from flexible spatial…

We present Self-Remixing, a novel self-supervised speech separation method, which refines a pre-trained separation model in an unsupervised manner. The proposed method consists of a shuffler module and a solver module, and they grow…

Speech is one of the most effective means of communication and is full of information that helps the transmission of utterer's thoughts. However, mainly due to the cumbersome processing of acoustic features, phoneme or word posterior…

With the rapid development of language models, the number of small language models (SLMs) has grown significantly. Although they do not achieve state-of-the-art accuracy, they are more efficient and often excel at specific tasks. This…

Intelligent reflecting surface (IRS) is a promising technology to extend the wireless signal coverage and support the high performance communication. By intelligently adjusting the reflection coefficients of a large number of passive…

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…

This paper quantifies the benefits and limitations of cooperative communications by providing a statistical analysis of the downlink in network multiple-input multiple-output (MIMO) systems. We consider an idealized model where the…

In scenarios where devices are too small to support MIMO antenna arrays, symbol-level cooperation may be used to pool the resources of distributed single-antenna devices to create a virtual MIMO antenna array. We address design fundamentals…

Continuous speech separation (CSS) is a recently proposed framework which aims at separating each speaker from an input mixture signal in a streaming fashion. Hereafter we perform an evaluation study on practical design considerations for a…

Training of large language models (LLMs) is typically distributed across a large number of accelerators to reduce training time. Since internal states and parameter gradients need to be exchanged at each and every single gradient step, all…

We present a novel approach to Speaker Diarization (SD) by leveraging text-based methods focused on Sentence-level Speaker Change Detection within dialogues. Unlike audio-based SD systems, which are often challenged by audio quality and…

The deep learning trend has recently impacted a variety of fields, including communication systems, where various approaches have explored the application of neural networks in place of traditional designs. Neural networks flexibly allow…

The advent of the transformer has sparked a quick growth in the size of language models, far outpacing hardware improvements. (Dense) transformers are expected to reach the trillion-parameter scale in the near future, for which training…

Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…

In this paper we propose a method of single-channel speaker-independent multi-speaker speech separation for an unknown number of speakers. As opposed to previous works, in which the number of speakers is assumed to be known in advance and…

Model-as-a-Service (MaaS) platforms face diverse Service Level Objective (SLO) requirements stemming from various large language model (LLM) applications, manifested in contextual complexity, first-token latency, and between-token latency.…

In this paper, we quantify performance gain achieved if SISO system is replaced with 4x4 MIMO in WLAN setting compatible with IEEE 802.11n standard. We compare throughput and power savings in MIMO by taking field measurements at various…

The goal of a speech-to-image transform is to produce a photo-realistic picture directly from a speech signal. Recently, various studies have focused on this task and have achieved promising performance. However, current speech-to-image…