English
Related papers

Related papers: Sparse deepfake detection promotes better disentan…

200 papers

Sparse autoencoders (SAEs) decompose neural activations into interpretable features. A widely adopted variant, the TopK SAE, reconstructs each token from its K most active latents. However, this approach is inefficient, as some tokens carry…

Machine Learning · Computer Science 2025-09-01 Narmeen Oozeer , Nirmalendu Prakash , Michael Lan , Alice Rigg , Amirali Abdullah

Explaining the decisions made by audio spoofing detection models is crucial for fostering trust in detection outcomes. However, current research on the interpretability of detection models is limited to applying XAI tools to post-trained…

Sound · Computer Science 2025-07-28 Menglu Li , Xiao-Ping Zhang

Recently, it has been observed that when representations are learnt in a way that encourages sparsity, improved performance is obtained on classification tasks. These methods involve combinations of activation functions, sampling steps and…

Machine Learning · Computer Science 2014-03-25 Alireza Makhzani , Brendan Frey

With the rapid development of speech conversion and speech synthesis algorithms, automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. In recent years, researchers had proposed a number of anti-spoofing methods…

Sound · Computer Science 2022-12-23 Qiaowei Ma , Jinghui Zhong , Yitao Yang , Weiheng Liu , Ying Gao , Wing W. Y. Ng

In this paper, we propose a novel self-distillation method for fake speech detection (FSD), which can significantly improve the performance of FSD without increasing the model complexity. For FSD, some fine-grained information is very…

Sound · Computer Science 2023-03-03 Jun Xue , Cunhang Fan , Jiangyan Yi , Chenglong Wang , Zhengqi Wen , Dan Zhang , Zhao Lv

We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also being more amenable to human interpretation, as we demonstrate…

Machine Learning · Computer Science 2021-05-12 Eric Wong , Shibani Santurkar , Aleksander Mądry

Despite the tremendous success of automatic speech recognition (ASR) with the introduction of deep learning, its performance is still unsatisfactory in many real-world multi-talker scenarios. Speaker separation excels in separating…

Sound · Computer Science 2025-03-25 Yufeng Yang , Hassan Taherian , Vahid Ahmadi Kalkhorani , DeLiang Wang

Subsampling layers play a crucial role in deep nets by discarding a portion of an activation map to reduce its spatial dimensions. This encourages the deep net to learn higher-level representations. Contrary to this motivation, we…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Chiao-An Yang , Ziwei Liu , Raymond A. Yeh

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Machine Learning · Computer Science 2025-07-30 Viktoria Schuster

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Machine Learning · Computer Science 2025-06-09 Yin Lu , Xuening Zhu , Tong He , David Wipf

The SAFE Challenge evaluates synthetic speech detection across three tasks: unmodified audio, processed audio with compression artifacts, and laundered audio designed to evade detection. We systematically explore self-supervised learning…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-08 Hashim Ali , Surya Subramani , Lekha Bollinani , Nithin Sai Adupa , Sali El-Loh , Hafiz Malik

End-to-end speech recognition systems have achieved competitive results compared to traditional systems. However, the complex transformations involved between layers given highly variable acoustic signals are hard to analyze. In this paper,…

Computation and Language · Computer Science 2019-11-05 Chung-Yi Li , Pei-Chieh Yuan , Hung-Yi Lee

Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…

Machine Learning · Computer Science 2024-08-06 Charles O'Neill , Christine Ye , Kartheik Iyer , John F. Wu

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…

Sound · Computer Science 2022-01-25 Zhengyang Chen , Sanyuan Chen , Yu Wu , Yao Qian , Chengyi Wang , Shujie Liu , Yanmin Qian , Michael Zeng

Conformer has achieved impressive results in Automatic Speech Recognition (ASR) by leveraging transformer's capturing of content-based global interactions and convolutional neural network's exploiting of local features. In Conformer, two…

Computation and Language · Computer Science 2022-09-02 Xianchao Wu

ASVspoof5, the fifth edition of the ASVspoof series, is one of the largest global audio security challenges. It aims to advance the development of countermeasure (CM) to discriminate bonafide and spoofed speech utterances. In this paper, we…

Sound · Computer Science 2024-08-14 Yuankun Xie , Xiaopeng Wang , Zhiyong Wang , Ruibo Fu , Zhengqi Wen , Haonan Cheng , Long Ye

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…

Machine Learning · Computer Science 2026-03-04 Xuan Yang , Jiayu Liu , Yuhang Lai , Hao Xu , Zhenya Huang , Ning Miao

While the technologies empowering malicious audio deepfakes have dramatically evolved in recent years due to generative AI advances, the same cannot be said of global research into spoofing (deepfake) countermeasures. This paper highlights…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-16 Héctor Delgado , Giorgio Ramondetti , Emanuele Dalmasso , Gennady Karvitsky , Daniele Colibro , Haydar Talib

The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to…

Sound · Computer Science 2024-07-11 Marcella Astrid , Enjie Ghorbel , Djamila Aouada

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alone is an imperfect proxy for interpretability, and current training objectives often…

Machine Learning · Computer Science 2026-04-09 Vivek Narayanaswamy , Kowshik Thopalli , Bhavya Kailkhura , Wesam Sakla
‹ Prev 1 4 5 6 7 8 10 Next ›