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