English
Related papers

Related papers: Array Geometry-Robust Attention-Based Neural Beamf…

200 papers

In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monotonic chunkwise attention (MoChA) and head-synchronous…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-14 Mohan Li , Shucong Zhang , Catalin Zorila , Rama Doddipatla

Transformer-based end-to-end neural speaker diarization (EEND) models utilize the multi-head self-attention (SA) mechanism to enable accurate speaker label prediction in overlapped speech regions. In this study, to enhance the training…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-03 Ye-Rin Jeoung , Joon-Young Yang , Jeong-Hwan Choi , Joon-Hyuk Chang

We propose a novel adversarial speaker adaptation (ASA) scheme, in which adversarial learning is applied to regularize the distribution of deep hidden features in a speaker-dependent (SD) deep neural network (DNN) acoustic model to be close…

Machine Learning · Computer Science 2019-04-30 Zhong Meng , Jinyu Li , Yifan Gong

This work investigates a robust resource allocation framework for a downlink multi-user communication system integrating movable antennas (MAs) and reconfigurable intelligent surfaces (RISs) under the rate-splitting multiple access (RSMA)…

Signal Processing · Electrical Eng. & Systems 2026-05-12 Muhammad Asif , Asim Ihsan , Zhongliang Wang , Manzoor Ahmed , Xingwang Li , Arumugam Nallanathan , Symeon Chatzinotas

Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the self-attention mechanism only processes information at the…

Machine Learning · Computer Science 2021-08-12 Yao Zhang , Yunpu Ma , Thomas Seidl , Volker Tresp

Movable antenna (MA)-enabled near-field (NF) communications offer significant potential for 6G, yet existing designs often neglect the practical constraints of hybrid beamforming (HBF) for extremely large-scale MIMO (XL-MIMO). Conversely,…

Information Theory · Computer Science 2026-05-11 Xiangqian Xu , Songjie Yang , Arumugam Nallanathan

Deep spatially selective filters achieve high-quality enhancement with real-time capable architectures for stationary speakers of known directions. To retain this level of performance in dynamic scenarios when only the speakers' initial…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-26 Jakob Kienegger , Timo Gerkmann

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…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-15 Yang Yang , Shao-Fu Shih , Hakan Erdogan , Jamie Menjay Lin , Chehung Lee , Yunpeng Li , George Sung , Matthias Grundmann

Speech enhancement (SE) aims to improve the clarity, intelligibility, and quality of speech signals for various speech enabled applications. However, air-conducted (AC) speech is highly susceptible to ambient noise, particularly in low…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-14 Fuyuan Feng , Longting Xu , Rohan Kumar Das

We propose BeamTransformer, an efficient architecture to leverage beamformer's edge in spatial filtering and transformer's capability in context sequence modeling. BeamTransformer seeks to optimize modeling of sequential relationship among…

Sound · Computer Science 2021-09-10 Siqi Zheng , Shiliang Zhang , Weilong Huang , Qian Chen , Hongbin Suo , Ming Lei , Jinwei Feng , Zhijie Yan

In this paper, we study several microphone channel selection and weighting methods for robust automatic speech recognition (ASR) in noisy conditions. For channel selection, we investigate two methods based on the maximum likelihood (ML)…

Sound · Computer Science 2016-10-04 Zhaofeng Zhang , Xiong Xiao , Longbiao Wang , EngSiong Chng , Haizhou Li

In recent advancements in audio self-supervised representation learning, the standard Transformer architecture has emerged as the predominant approach, yet its attention mechanism often allocates a portion of attention weights to irrelevant…

Sound · Computer Science 2025-07-04 Junyu Wang , Tianrui Wang , Meng Ge , Longbiao Wang , Jianwu Dang

This paper addresses the issue of active speaker detection (ASD) in noisy environments and formulates a robust active speaker detection (rASD) problem. Existing ASD approaches leverage both audio and visual modalities, but non-speech sounds…

Multimedia · Computer Science 2024-04-02 Siva Sai Nagender Vasireddy , Chenxu Zhang , Xiaohu Guo , Yapeng Tian

Modern smart glasses leverage advanced audio sensing and machine learning technologies to offer real-time transcribing and captioning services, considerably enriching human experiences in daily communications. However, such systems…

Acoustic beamforming aims to focus acoustic signals to a specific direction and suppress undesirable interferences from other directions. Despite its flexibility and steerability, beamforming with circular microphone arrays suffers from…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-27 Sipei Zhao , Fei Ma

This paper investigates the movable antenna (MA)- assisted downlink non-orthogonal multiple access (NOMA) network to maximize system throughput. In the considered scenario, both the base station (BS) and users are equipped with MA, and a…

Signal Processing · Electrical Eng. & Systems 2025-07-28 Yufeng Zhou , Wen Chen , Qingqing Wu , Xusheng Zhu , Zhendong Li , Kunlun Wang , Qiong Wu

Audio Telepresence (AT) aims to create an immersive experience of the audio scene at the far end for the user(s) at the near end. The application of AT could encompass scenarios with varying degrees of emphasis on signal enhancement and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-22 Yicheng Hsu , Mingsian R. Bai

Multimodal large language models have demonstrated strong ability in capturing semantic representations for multimodal sentiment analysis. Their capacity to learn stable and generalizable multimodal features is limited, however, by the…

Machine Learning · Computer Science 2026-05-26 Jiazhang Liang , Jianheng Dai , Miaosen Luo , Menghua Jiang , Sijie Mai

In ultrasound (US) imaging, individual channel RF measurements are back-propagated and accumulated to form an image after applying specific delays. While this time reversal is usually implemented using a hardware- or software-based…

Image and Video Processing · Electrical Eng. & Systems 2019-07-17 Shujaat Khan , Jaeyoung Huh , Jong Chul Ye

Supervised deep learning has gained significant attention for speech enhancement recently. The state-of-the-art deep learning methods perform the task by learning a ratio/binary mask that is applied to the mixture in the time-frequency…

Sound · Computer Science 2020-02-03 Bahareh Tolooshams , Ritwik Giri , Andrew H. Song , Umut Isik , Arvindh Krishnaswamy