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

High quality speech capture has been widely studied for both voice communication and human computer interface reasons. To improve the capture performance, we can often find multi-microphone speech enhancement techniques deployed on various…

This paper investigates a joint beamforming design in a multiuser multiple-input single-output (MISO) communication network aided with an intelligent reflecting surface (IRS) panel. The symbol-level precoding (SLP) is adopted to enhance the…

Conditional sound separation in multi-source audio mixtures without having access to single source sound data during training is a long standing challenge. Existing mix-and-separate based methods suffer from significant performance drop…

Real-time single-channel speech separation aims to unmix an audio stream captured from a single microphone that contains multiple people talking at once, environmental noise, and reverberation into multiple de-reverberated and noise-free…

Modern large-scale language model pre-training relies heavily on the single program multiple data (SPMD) paradigm, which requires tight coupling across accelerators. Due to this coupling, transient slowdowns, hardware failures, and…

This paper examines the implications of using the Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) as both evaluation and training objective in supervised speech separation, when the training references contain noise, as is the case with…

Speech Foundation Models have gained significant attention recently. Prior works have shown that the fusion of representations from multiple layers of the same model or the fusion of multiple models can improve performance on downstream…

General audio source separation is a key capability for multimodal AI systems that can perceive and reason about sound. Despite substantial progress in recent years, existing separation models are either domain-specific, designed for fixed…

Multiple-input multiple-output (MIMO) has been a key technology of wireless communications for decades. A typical MIMO system employs antenna arrays with the inter-antenna spacing being half of the signal wavelength, which we term as…

This paper addresses the challenge of speaker separation, which remains an active research topic despite the promising results achieved in recent years. These results, however, often degrade in real recording conditions due to the presence…

We consider the problem of audio voice separation for binaural applications, such as earphones and hearing aids. While today's neural networks perform remarkably well (separating $4+$ sources with 2 microphones) they assume a known or fixed…

Although fully end-to-end speaker diarization systems have made significant progress in recent years, modular systems often achieve superior results in real-world scenarios due to their greater adaptability and robustness. Historically,…

In this paper, the design of binary sequences exhibiting low values of aperiodic/periodic correlation functions, in terms of Integrated Sidelobe Level (ISL), is pursued via a learning-inspired method. Specifcally, the synthesis of either a…

Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires…

Neural networks have led to tremendous performance gains for single-task speech enhancement, such as noise suppression and acoustic echo cancellation (AEC). In this work, we evaluate whether it is more useful to use a single joint or…

This study considers a dual-polarized intelligent reflecting surface (DP-IRS)-assisted multiple-input multiple-output (MIMO) single-user wireless communication system. The transmitter and receiver are equipped with DP antennas, and each…

The performance of single channel source separation algorithms has improved greatly in recent times with the development and deployment of neural networks. However, many such networks continue to operate on the magnitude spectrogram of a…

Large Language Models (LLMs) have enabled dynamic reasoning in automated data analytics, yet recent multi-agent systems remain limited by rigid, single-path workflows that restrict strategic exploration and often lead to suboptimal…

Flexible intelligent metasurface (FIM) technology holds immense potential for increasing the spectral efficiency and energy efficiency of wireless networks. In contrast to traditional rigid reconfigurable intelligent surfaces (RIS), an FIM…

Existing CNN-based speech separation models face local receptive field limitations and cannot effectively capture long time dependencies. Although LSTM and Transformer-based speech separation models can avoid this problem, their high…