相关论文: Audio Mamba: Pretrained Audio State Space Model Fo…

Keyword spotting (KWS) is an essential task in speech processing. It is widely used in voice assistants and smart devices. Deep learning models like CNNs, RNNs, and Transformers have performed well in KWS. However, they often struggle to…

The core challenge in industrial equipment anoma lous sound detection (ASD) lies in modeling the time-frequency coupling characteristics of acoustic features. Existing modeling methods are limited by local receptive fields, making it…

In recent speech enhancement (SE) research, transformer and its variants have emerged as the predominant methodologies. However, the quadratic complexity of the self-attention mechanism imposes certain limitations on practical deployment.…

State-space modeling has emerged as a powerful paradigm for sequence analysis in various tasks such as natural language processing, time-series forecasting, and signal processing. In this work, we propose an \emph{Adaptive State-Space…

Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal…

This work aims to investigate the use of a recently proposed, attention-free, scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task. In particular, we employ Mamba to deploy different regression-based SE models…

The topic of speech separation involves separating mixed speech with multiple overlapping speakers into several streams, with each stream containing speech from only one speaker. Many highly effective models have emerged and proliferated…

Sound source localization (SSL) determines the position of sound sources using multi-channel audio data. It is commonly used to improve speech enhancement and separation. Extracting spatial features is crucial for SSL, especially in…

The essence of audio-visual segmentation (AVS) lies in locating and delineating sound-emitting objects within a video stream. While Transformer-based methods have shown promise, their handling of long-range dependencies struggles due to…

State space models (SSMs) for language modelling promise an efficient and performant alternative to quadratic-attention Transformers, yet show variable performance on recalling basic information from the context. While performance on…

Tooth segmentation is a pivotal step in modern digital dentistry, essential for applications across orthodontic diagnosis and treatment planning. Despite its importance, this process is fraught with challenges due to the high noise and low…

While audio quality is a key performance metric for various audio processing tasks, including generative modeling, its objective measurement remains a challenge. Audio-Language Models (ALMs) are pre-trained on audio-text pairs that may…

Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based…

Video understanding requires the extraction of rich spatio-temporal representations, which transformer models achieve through self-attention. Unfortunately, self-attention poses a computational burden. In NLP, Mamba has surfaced as an…

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation costs high, limiting the number of points that can be processed simultaneously…

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

State space models (SSMs) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently demonstrated significant promise in long-sequence modeling. Since the self-attention mechanism in transformers has quadratic…

Convolutional neural networks have primarily led 3D medical image segmentation but may be limited by small receptive fields. Transformer models excel in capturing global relationships through self-attention but are challenged by high…

The Interspeech 2025 URGENT Challenge aimed to advance universal, robust, and generalizable speech enhancement by unifying speech enhancement tasks across a wide variety of conditions, including seven different distortion types and five…