English
Related papers

Related papers: Supervector Compression Strategies to Speed up I-V…

200 papers

In recent years, the rapid progress in speaker verification (SV) technology has been driven by the extraction of speaker representations based on deep learning. However, such representations are still vulnerable to emotion variability. To…

Sound · Computer Science 2025-05-27 Jingguang Tian , Xinhui Hu , Xinkang Xu

Transformer-based speech recognition models have achieved great success due to the self-attention (SA) mechanism that utilizes every frame in the feature extraction process. Especially, SA heads in lower layers capture various phonetic…

Computation and Language · Computer Science 2022-07-13 Kyuhong Shim , Wonyong Sung

Non-Gaussianity-based Independent Vector Extraction leads to the famous one-unit FastICA/FastIVA algorithm when the likelihood function is optimized using an approximate Newton-Raphson algorithm under the orthogonality constraint. In this…

Signal Processing · Electrical Eng. & Systems 2024-07-15 Zbyněk Koldovský , Jiří Málek , Jaroslav Čmejla , Stephen O'Regan

Meta-learning has recently become a research hotspot in speaker verification (SV). We introduce two methods to improve the meta-learning training for SV in this paper. For the first method, a backbone embedding network is first jointly…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-04 Yafeng Chen , Wu Guo , Bin Gu

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…

Sound · Computer Science 2020-12-18 Mostafa Sadeghi , Simon Leglaive , Xavier Alameda-PIneda , Laurent Girin , Radu Horaud

This paper proposes an extension of principal component analysis for Gaussian process (GP) posteriors, denoted by GP-PCA. Since GP-PCA estimates a low-dimensional space of GP posteriors, it can be used for meta-learning, which is a…

Machine Learning · Statistics 2023-04-07 Hideaki Ishibashi , Shotaro Akaho

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-04 Mufan Sang , John H. L. Hansen

Fine-tuning large language models (LLMs) is crucial for improving their performance on downstream tasks, but full-parameter fine-tuning (Full-FT) is computationally expensive and memory-intensive. Parameter-efficient fine-tuning (PEFT)…

Computation and Language · Computer Science 2026-05-12 Longteng Zhang , Lin Zhang , Shaohuai Shi , Xiaowen Chu , Bo Li

Inference for Variational Autoencoders (VAEs) consists of learning two models: (1) a generative model, which transforms a simple distribution over a latent space into the distribution over observed data, and (2) an inference model, which…

Machine Learning · Statistics 2024-06-14 Yaniv Yacoby , Weiwei Pan , Finale Doshi-Velez

Principal component analysis (PCA) is perhaps the most widely used method for data dimensionality reduction. A key question in PCA is deciding how many factors to retain. This manuscript describes a new approach to automatically selecting…

Methodology · Statistics 2026-02-10 Enes Makalic , Daniel F. Schmidt

The speech feature extraction has been a key focus in robust speech recognition research; it significantly affects the recognition performance. In this paper, we first study a set of different features extraction methods such as linear…

Computation and Language · Computer Science 2014-07-01 Imen Trabelsi , Dorra Ben Ayed

Despite extensive research, open-vocabulary segmentation methods still struggle to generalize across diverse domains. To reduce the computational cost of adapting Vision-Language Models (VLMs) while preserving their pre-trained knowledge,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Yong Xien Chng , Xuchong Qiu , Yizeng Han , Kai Ding , Wan Ding , Gao Huang

Principal Component Analysis (PCA) is known to be the most widely applied dimensionality reduction approach. A lot of improvements have been done on the traditional PCA, in order to obtain optimal results in the dimensionality reduction of…

Computer Vision and Pattern Recognition · Computer Science 2020-09-28 Chisom Ezinne Ogbuanya

Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that…

Sound · Computer Science 2026-05-13 Adam Wynn , Jingyun Wang

Catastrophic forgetting is a well-documented challenge in model fine-tuning, particularly when the downstream domain has limited labeled data or differs substantially from the pre-training distribution. Existing parameter-efficient…

Machine Learning · Computer Science 2026-02-03 Peng Wang , Minghao Gu , Qiang Huang

Feature extraction and dimensionality reduction are important tasks in many fields of science dealing with signal processing and analysis. The relevance of these techniques is increasing as current sensory devices are developed with ever…

Machine Learning · Statistics 2013-10-21 Jerónimo Arenas-García , Kaare Brandt Petersen , Gustavo Camps-Valls , Lars Kai Hansen

Principal component analysis (PCA) is a classical and ubiquitous method for reducing data dimensionality, but it is suboptimal for heterogeneous data that are increasingly common in modern applications. PCA treats all samples uniformly so…

Statistics Theory · Mathematics 2021-12-02 David Hong , Kyle Gilman , Laura Balzano , Jeffrey A. Fessler

Vision-Language Models (VLMs) like CLIP have demonstrated remarkable generalization in zero- and few-shot settings, but adapting them efficiently to decentralized, heterogeneous data remains a challenge. While prompt tuning has emerged as a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Sajjad Ghiasvand , Mahnoosh Alizadeh , Ramtin Pedarsani

Factor models have been widely used in economics and finance. However, the heavy-tailed nature of macroeconomic and financial data is often neglected in the existing literature. To address this issue and achieve robustness, we propose an…

Methodology · Statistics 2023-03-30 Yong He , Lingxiao Li , Dong Liu , Wen-Xin Zhou

Unsupervised domain adaptation (UDA) is a critical challenge in the field of point cloud analysis. Previous works tackle the problem either by feature extractor adaptation to enable a shared classifier to distinguish domain-invariant…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Zicheng Wang , Zhen Zhao , Yiming Wu , Luping Zhou , Dong Xu