English
Related papers

Related papers: Representation Loss Minimization with Randomized S…

200 papers

Deepfakes are synthetic media generated using deep generative algorithms and have posed a severe societal and political threat. Apart from facial manipulation and synthetic voice, recently, a novel kind of deepfakes has emerged with either…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Vinaya Sree Katamneni , Ajita Rattani

This paper investigates the application of environmental feature representations for room verification tasks and acoustic meta-data estimation. Audio recordings contain both speaker and non-speaker information. We refer to the…

Sound · Computer Science 2022-03-10 Desmond Caulley

This paper describes sound event localization and detection (SELD) for spatial audio recordings captured by firstorder ambisonics (FOA) microphones. In this task, one may train a deep neural network (DNN) using FOA data annotated with the…

Sound · Computer Science 2024-10-31 Yoto Fujita , Yoshiaki Bando , Keisuke Imoto , Masaki Onishi , Kazuyoshi Yoshii

Rapid advancements in speech synthesis and voice conversion bring convenience but also new security risks, creating an urgent need for effective audio deepfake detection. Although current models perform well, their effectiveness diminishes…

Diffusion Transformers have become a dominant paradigm in visual generation, yet their low inference efficiency remains a key bottleneck hindering further advancement. Among common training-free techniques, caching offers high acceleration…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Tong Shao , Yusen Fu , Guoying Sun , Jingde Kong , Zhuotao Tian , Jingyong Su

Deep embedding based text-independent speaker verification has demonstrated superior performance to traditional methods in many challenging scenarios. Its loss functions can be generally categorized into two classes, i.e., verification and…

Machine Learning · Computer Science 2019-11-20 Zhongxin Bai , Xiao-Lei Zhang , Jingdong Chen

Tensor-valued data benefits greatly from dimension reduction as the reduction in size is exponential in the number of modes. To achieve maximal reduction without loss in information, our objective in this work is to give an automated…

Methodology · Statistics 2022-07-22 Una Radojicic , Niko Lietzen , Klaus Nordhausen , Joni Virta

An analysis of high-dimensional data can offer a detailed description of a system but is often challenged by the curse of dimensionality. General dimensionality reduction techniques can alleviate such difficulty by extracting a few…

Methodology · Statistics 2021-09-28 Di Bo , Hoon Hwangbo , Vinit Sharma , Corey Arndt , Stephanie C. TerMaath

Generalisation -- the ability of a model to perform well on unseen data -- is crucial for building reliable deepfake detectors. However, recent studies have shown that the current audio deepfake models fall short of this desideratum. In…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-14 Octavian Pascu , Adriana Stan , Dan Oneata , Elisabeta Oneata , Horia Cucu

Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in…

Machine Learning · Computer Science 2023-12-13 Julia Huiming Wang , Dexter Tsin , Tatiana Engel

In our "big data" age, the size and complexity of data is steadily increasing. Methods for dimension reduction are ever more popular and useful. Two distinct types of dimension reduction are "data-oblivious" methods such as random…

Statistics Theory · Mathematics 2021-03-30 Fan Yang , Sifan Liu , Edgar Dobriban , David P. Woodruff

State-of-the-art sound event detection (SED) methods usually employ a series of convolutional neural networks (CNNs) to extract useful features from the input audio signal, and then recurrent neural networks (RNNs) to model longer temporal…

High-dimensional tensor-valued predictors arise in modern applications, increasingly as learned representations from neural networks. Existing tensor classification methods rely on sparsity or Tucker structures and often lack theoretical…

Machine Learning · Computer Science 2025-12-16 Elynn Chen , Yuefeng Han , Jiayu Li

Deep reinforcement learning requires a heavy price in terms of sample efficiency and overparameterization in the neural networks used for function approximation. In this work, we use tensor factorization in order to learn more compact…

Machine Learning · Computer Science 2019-11-27 Pierre H. Richemond , Arinbjörn Kolbeinsson , Yike Guo

We present an approach called guaranteed block autoencoder that leverages Tensor Correlations (GBATC) for reducing the spatiotemporal data generated by computational fluid dynamics (CFD) and other scientific applications. It uses a…

Machine Learning · Computer Science 2024-04-30 Jaemoon Lee , Ki Sung Jung , Qian Gong , Xiao Li , Scott Klasky , Jacqueline Chen , Anand Rangarajan , Sanjay Ranka

Spectral dimensionality reduction algorithms are widely used in numerous domains, including for recognition, segmentation, tracking and visualization. However, despite their popularity, these algorithms suffer from a major limitation known…

Machine Learning · Computer Science 2018-01-03 Yochai Blau , Tomer Michaeli

Classical methods for acoustic scene mapping require the estimation of time difference of arrival (TDOA) between microphones. Unfortunately, TDOA estimation is very sensitive to reverberation and additive noise. We introduce an unsupervised…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-14 Idan Cohen , Ofir Lindenbaum , Sharon Gannot

Foundation models such as Wav2Vec2 excel at representation learning in speech tasks, including audio deepfake detection. However, after being fine-tuned on a fixed set of bonafide and spoofed audio clips, they often fail to generalize to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-18 Janne Laakkonen , Ivan Kukanov , Ville Hautamäki

Automatic speaker verification (ASV) systems are highly vulnerable to presentation attacks, also called spoofing attacks. Replay is among the simplest attacks to mount - yet difficult to detect reliably. The generalization failure of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-24 Bhusan Chettri , Tomi Kinnunen , Emmanouil Benetos

Deep neural networks perform remarkably well on image classification tasks but remain vulnerable to carefully crafted adversarial perturbations. This work revisits linear dimensionality reduction as a simple, data-adapted defense. We…

Machine Learning · Computer Science 2025-10-08 Killian Steunou , Théo Druilhe , Sigurd Saue
‹ Prev 1 8 9 10 Next ›