相关论文: Local spectral attention for full-band speech enha…

Linear recurrent models offer linear-time sequence processing but often suffer from suboptimal long-range memory. We trace this to the decay spectrum: for $N$ channels, random initialization collapses the minimum spectral gap to…

Efficient spectrum management in massive-scale wireless networks is increasingly challenged by explosive action spaces and the computational intractability of traditional optimization. This study proposes a Large-Scale LLM-Driven Spectrum…

The self-attention mechanism prevails in modern machine learning. It has an interesting functionality of adaptively selecting tokens from an input sequence by modulating the degree of attention localization, which many researchers speculate…

In this paper, we present a region-based pLSA model to accomplish the task of total scene annotation. To be more specific, we not only properly generate a list of tags for each image, but also localizing each region with its corresponding…

Regularized linear discriminant analysis (RLDA) is a widely used tool for classification and dimensionality reduction, but its performance in high-dimensional scenarios is inconsistent. Existing theoretical analyses of RLDA often lack clear…

Bayesian estimation of short-time spectral amplitude is one of the most predominant approaches for the enhancement of the noise corrupted speech. The performance of these estimators are usually significantly improved when any perceptually…

Speech enhancement techniques based on deep learning have brought significant improvement on speech quality and intelligibility. Nevertheless, a large gain in speech quality measured by objective metrics, such as perceptual evaluation of…

Modeling long sequences is crucial for various large-scale models; however, extending existing architectures to handle longer sequences presents significant technical and resource challenges. In this paper, we propose an efficient and…

Attention mechanisms have emerged as important tools that boost the performance of deep models by allowing them to focus on key parts of learned embeddings. However, current attention mechanisms used in speaker recognition tasks fail to…

Current Transformer methods for Multivariate Time-Series Forecasting (MTSF) are all based on the conventional attention mechanism. They involve sequence embedding and performing a linear projection of Q, K, and V, and then computing…

Target speaker information can be utilized in speech enhancement (SE) models to more effectively extract the desired speech. Previous works introduce the speaker embedding into speech enhancement models by means of concatenation or affine…

Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remained structurally unchanged. Local Linear Attention (LLA) is an attention mechanism derived…

This paper presents a spectral attention-driven reinforcement learning based intelligent method for effective and efficient detection of important signals in a wideband spectrum. In the work presented in this paper, it is assumed that the…

In this paper we propose a lightweight model for frequency bandwidth extension of speech signals, increasing the sampling frequency from 8kHz to 16kHz while restoring the high frequency content to a level almost indistinguishable from the…

Mamba, a selective state-space model (SSM), has emerged as an efficient alternative to Transformers for speech modeling, enabling long-sequence processing with linear complexity. While effective in speech separation, existing approaches,…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

We propose a method using a long short-term memory (LSTM) network to estimate the noise power spectral density (PSD) of single-channel audio signals represented in the short time Fourier transform (STFT) domain. An LSTM network common to…

Many applications of speech technology require more and more audio data. Automatic assessment of the quality of the collected recordings is important to ensure they meet the requirements of the related applications. However, effective and…

We propose SLOT (Sample-specific Language Model Optimization at Test-time), a novel and parameter-efficient test-time inference approach that enhances a language model's ability to more accurately respond to individual prompts. Existing…

In recent years, the Transformer architecture has proven to be very successful in sequence processing, but its application to other data structures, such as graphs, has remained limited due to the difficulty of properly defining positions.…