Related papers: IMSE: Efficient U-Net-based Speech Enhancement usi…

Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are becoming larger to capture more complex capabilities, their…

This study investigates small-scale pretraining for Small Language Models (SLMs) to enable efficient use of limited data and compute, improve accessibility in low-resource settings and reduce costs. To enhance long-context extrapolation in…

Intent detection is a crucial task in any Natural Language Understanding (NLU) system and forms the foundation of a task-oriented dialogue system. To build high-quality real-world conversational solutions for edge devices, there is a need…

Channel State Information (CSI) Feedback plays a crucial role in achieving higher gains through beamforming. However, for a massive MIMO system, this feedback overhead is huge and grows linearly with the number of antennas. To reduce the…

Analyzing individual emotions during group conversation is crucial in developing intelligent agents capable of natural human-machine interaction. While reliable emotion recognition techniques depend on different modalities (text, audio,…

Self-attention scales quadratically with sequence length, limiting transformer-based speech models on edge devices. We introduce the Learnable Pulse Accumulator (LPA), an O(n) replacement that substitutes key-query dot products with learned…

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Multi-Head Latent Attention (MLA), introduced in DeepSeek-V2, improves the efficiency of large language models by projecting query, key, and value tensors into a compact latent space. This architectural change reduces the KV-cache size and…

Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio…

In this work, we study robust deep learning against abnormal training data from the perspective of example weighting built in empirical loss functions, i.e., gradient magnitude with respect to logits, an angle that is not thoroughly studied…

The Transformer architecture has proven to be highly effective for Automatic Speech Recognition (ASR) tasks, becoming a foundational component for a plethora of research in the domain. Historically, many approaches have leaned on…

Vision-Language Models (vLLMs) have emerged as powerful architectures for joint reasoning over visual and textual inputs, enabling breakthroughs in image captioning, cross modal retrieval, and multimodal dialogue. However, as these models…

Balancing accuracy and latency on high-resolution images is a critical challenge for lightweight models, particularly for Transformer-based architectures that often suffer from excessive latency. To address this issue, we introduce…

Complex spectrum and magnitude are considered as two major features of speech enhancement and dereverberation. Traditional approaches always treat these two features separately, ignoring their underlying relationship. In this paper, we…

Single-channel speech enhancement (SE) is an important task in speech processing. A widely used framework combines an analysis/synthesis filterbank with a mask prediction network, such as the Conv-TasNet architecture. In such systems, the…

Deep learning based speech denoising still suffers from the challenge of improving perceptual quality of enhanced signals. We introduce a generalized framework called Perceptual Ensemble Regularization Loss (PERL) built on the idea of…

Recent advancements in scaling up models have significantly improved performance in Automatic Speech Recognition (ASR) tasks. However, training large ASR models from scratch remains costly. To address this issue, we introduce UME, a novel…

Current speech enhancement (SE) research has largely neglected channel attention and spatial attention, and encoder-decoder architecture-based networks have not adequately considered how to provide efficient inputs to the intermediate…

Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…

In this paper, we propose long short term memory speech enhancement network (LSTMSE-Net), an audio-visual speech enhancement (AVSE) method. This innovative method leverages the complementary nature of visual and audio information to boost…