相关论文: Unsupervised Improved MVDR Beamforming for Sound E…

Speech enhancement and source localization has been active research for several decades with a wide range of real-world applications. Recently, the Deep Complex Convolution Recurrent network (DCCRN) has yielded impressive enhancement…

In this paper, we propose a speech enhancement method us ing dual-path Multi-Channel Linear Prediction (MCLP) filters and multi-norm beamforming. Specifically, the MCLP part in the proposed method is designed with dual-path filters in both…

In this letter, we present a novel multi-talker minimum variance distortionless response (MVDR) beamforming as the front-end of an automatic speech recognition (ASR) system in a dinner party scenario. The CHiME-5 dataset is selected to…

Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the success of self-supervised learning models in single-channel…

In recent years, many deep learning techniques for single-channel sound source separation have been proposed using recurrent, convolutional and transformer networks. When multiple microphones are available, spatial diversity between…

Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision.…

Ultrasound imaging, despite its widespread use in medicine, often suffers from various sources of noise and artifacts that impact the signal-to-noise ratio and overall image quality. Enhancing ultrasound images requires a delicate balance…

Future multi-input multi-output (MIMO) wireless communications systems will use beamforming as a first-step towards realizing the capacity requirements necessitated by the exponential increase in data demands. The focus of this work is on…

Monaural source separation is important for many real world applications. It is challenging because, with only a single channel of information available, without any constraints, an infinite number of solutions are possible. In this paper,…

Speech separation with several speakers is a challenging task because of the non-stationarity of the speech and the strong signal similarity between interferent sources. Current state-of-the-art solutions can separate well the different…

Spatial clustering techniques can achieve significant multi-channel noise reduction across relatively arbitrary microphone configurations, but have difficulty incorporating a detailed speech/noise model. In contrast, LSTM neural networks…

In this paper, we are interested in audio-visual speech separation given a single-channel audio recording as well as visual information (lips movements) associated with each speaker. We propose an unsupervised technique based on…

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and…

Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal enhancement. However, the textbook solutions for optimal…

Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an…

Deep Neural Network-based source separation methods usually train independent models to optimize for the separation of individual sources. Although this can lead to good performance for well-defined targets, it can also be computationally…

Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…

The majority of deep learning-based speech enhancement methods require paired clean-noisy speech data. Collecting such data at scale in real-world conditions is infeasible, which has led the community to rely on synthetically generated…

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…

This paper addresses the problem of species classification in bird song recordings. The massive amount of available field recordings of birds presents an opportunity to use machine learning to automatically track bird populations. However,…