English
Related papers

Related papers: Few-Shot Speech Deepfake Detection Adaptation with…

200 papers

This paper presents a speech enhancement method, where an adaptive threshold is statistically determined based on Gaussian modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of noisy speech. In order to…

Audio and Speech Processing · Electrical Eng. & Systems 2018-03-07 Md Tauhidul Islam , Celia Shahnaz

Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech…

Sound · Computer Science 2022-06-30 Takaaki Saeki , Kentaro Tachibana , Ryuichi Yamamoto

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of…

The widespread use of generative AI has shown remarkable success in producing highly realistic deepfakes, posing a serious threat to various voice biometric applications, including speaker verification, voice biometrics, audio conferencing,…

Sound · Computer Science 2025-09-10 Kutub Uddin , Muhammad Umar Farooq , Awais Khan , Khalid Mahmood Malik

Fine-tuning is a popular method for adapting text-to-speech (TTS) models to new speakers. However this approach has some challenges. Usually fine-tuning requires several hours of high quality speech per speaker. There is also that…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Cheng-Ping Hsieh , Subhankar Ghosh , Boris Ginsburg

Although few-shot learning has attracted much attention from the fields of image and audio classification, few efforts have been made on few-shot speaker identification. In the task of few-shot learning, overfitting is a tough problem…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-26 Yanxiong Li , Wucheng Wang , Hao Chen , Wenchang Cao , Wei Li , Qianhua He

Deep Gaussian processes (DGP) have appealing Bayesian properties, can handle variable-sized data, and learn deep features. Their limitation is that they do not scale well with the size of the data. Existing approaches address this using a…

Machine Learning · Computer Science 2019-05-20 Issam H. Laradji , Mark Schmidt , Vladimir Pavlovic , Minyoung Kim

The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused…

Multi-robot systems require scalable and federated methods to model complex environments under computational and communication constraints. Gaussian Processes (GPs) offer robust probabilistic modeling, but suffer from cubic computational…

Multiagent Systems · Computer Science 2026-02-13 Sanket A. Salunkhe , George P. Kontoudis

Recent research has highlighted a key issue in speech deepfake detection: models trained on one set of deepfakes perform poorly on others. The question arises: is this due to the continuously improving quality of Text-to-Speech (TTS)…

Sound · Computer Science 2024-06-13 Nicolas M. Müller , Nicholas Evans , Hemlata Tak , Philip Sperl , Konstantin Böttinger

Gaussian processes (GPs) play an essential role in biostatistics, scientific machine learning, and Bayesian optimization for their ability to provide probabilistic predictions and model uncertainty. However, GP inference struggles to scale…

Machine Learning · Computer Science 2025-10-29 Pratik Rathore , Zachary Frangella , Sachin Garg , Shaghayegh Fazliani , Michał Dereziński , Madeleine Udell

We consider Bayesian inference problems with computationally intensive likelihood functions. We propose a Gaussian process (GP) based method to approximate the joint distribution of the unknown parameters and the data. In particular, we…

Computation · Statistics 2018-03-15 Hongqiao Wang , Jinglai Li

This work explores a simple yet powerful lightweight adapter design for feed-forward 3D Gaussian Splatting (3DGS). Existing methods typically apply complex, architecture-specific designs on top of the generic pipeline of image feature…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Mingwei Xing , Xinliang Wang , Yifeng Shi

Bayesian inference in high-dimensional discrete-input additive noise models is a fundamental challenge in communication systems, as the support of the required joint a posteriori probability (APP) mass function grows exponentially with the…

Information Theory · Computer Science 2026-04-08 Luca Schmid , Dominik Sulz , Shrinivas Chimmalgi , Laurent Schmalen

Custom voice, a specific text to speech (TTS) service in commercial speech platforms, aims to adapt a source TTS model to synthesize personal voice for a target speaker using few speech data. Custom voice presents two unique challenges for…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-02 Mingjian Chen , Xu Tan , Bohan Li , Yanqing Liu , Tao Qin , Sheng Zhao , Tie-Yan Liu

Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images. In this context, recent research efforts have been aimed at designing more and more complex…

Computer Vision and Pattern Recognition · Computer Science 2022-02-21 Jun He , Richang Hong , Xueliang Liu , Mingliang Xu , Qianru Sun

Deep Gaussian Processes (DGPs) are multi-layer, flexible extensions of Gaussian processes but their training remains challenging. Sparse approximations simplify the training but often require optimization over a large number of inducing…

Machine Learning · Statistics 2021-07-20 Ayush Jain , P. K. Srijith , Mohammad Emtiyaz Khan

Recently, Large language models (LLMs) with in-context learning have demonstrated remarkable potential in handling neural machine translation. However, existing evidence shows that LLMs are prompt-sensitive and it is sub-optimal to apply…

Computation and Language · Computer Science 2025-01-06 Lei Tang , Jinghui Qin , Wenxuan Ye , Hao Tan , Zhijing Yang

Text-to-Speech (TTS) synthesis using deep learning relies on voice quality. Modern TTS models are advanced, but they need large amount of data. Given the growing computational complexity of these models and the scarcity of large,…

Sound · Computer Science 2023-10-10 Ze Liu

Gaussian processes (GPs) are a good choice for function approximation as they are flexible, robust to over-fitting, and provide well-calibrated predictive uncertainty. Deep Gaussian processes (DGPs) are multi-layer generalisations of GPs,…

Machine Learning · Statistics 2017-11-15 Hugh Salimbeni , Marc Deisenroth