English
Related papers

Related papers: A weighted-variance variational autoencoder model …

200 papers

In this work, we propose a novel variational Bayesian adaptive learning approach for cross-domain knowledge transfer to address acoustic mismatches between training and testing conditions, such as recording devices and environmental noise.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-28 Hu Hu , Sabato Marco Siniscalchi , Chao-Han Huck Yang , Chin-Hui Lee

Many factors influence speech yielding different renditions of a given sentence. Generative models, such as variational autoencoders (VAEs), capture this variability and allow multiple renditions of the same sentence via sampling. The…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-21 Penny Karanasou , Sri Karlapati , Alexis Moinet , Arnaud Joly , Ammar Abbas , Simon Slangen , Jaime Lorenzo Trueba , Thomas Drugman

Speech enhancement is a critical component of many user-oriented audio applications, yet current systems still suffer from distorted and unnatural outputs. While generative models have shown strong potential in speech synthesis, they are…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-11 Yen-Ju Lu , Zhong-Qiu Wang , Shinji Watanabe , Alexander Richard , Cheng Yu , Yu Tsao

With the development of deep learning, speech enhancement has been greatly optimized in terms of speech quality. Previous methods typically focus on the discriminative supervised learning or generative modeling, which tends to introduce…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-31 Nan Xu , Zhaolong Huang , Xiaonan Zhi

Text-to-speech synthesis (TTS) is a task to convert texts into speech. Two of the factors that have been driving TTS are the advancements of probabilistic models and latent representation learning. We propose a TTS method based on latent…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-19 Yusuke Yasuda , Tomoki Toda

We introduce a method for embedding words as probability densities in a low-dimensional space. Rather than assuming that a word embedding is fixed across the entire text collection, as in standard word embedding methods, in our Bayesian…

Computation and Language · Computer Science 2018-06-12 Arthur Bražinskas , Serhii Havrylov , Ivan Titov

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…

Computation and Language · Computer Science 2023-05-25 Linhan Zhang , Qian Chen , Wen Wang , Chong Deng , Xin Cao , Kongzhang Hao , Yuxin Jiang , Wei Wang

Many real-world problems require reasoning across multiple scales, demanding models which operate not on single data points, but on entire distributions. We introduce generative distribution embeddings (GDE), a framework that lifts…

Machine Learning · Computer Science 2026-02-23 Nic Fishman , Gokul Gowri , Peng Yin , Jonathan Gootenberg , Omar Abudayyeh

Variational Autoencoders are powerful models for unsupervised learning. However deep models with several layers of dependent stochastic variables are difficult to train which limits the improvements obtained using these highly expressive…

Machine Learning · Statistics 2016-05-30 Casper Kaae Sønderby , Tapani Raiko , Lars Maaløe , Søren Kaae Sønderby , Ole Winther

Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the…

Machine Learning · Computer Science 2019-12-02 Le Fang , Chunyuan Li , Jianfeng Gao , Wen Dong , Changyou Chen

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel…

Sound · Computer Science 2021-06-14 Jaehyeon Kim , Jungil Kong , Juhee Son

We propose a novel spectral generative modeling framework for natural language processing that jointly learns a global time varying Fourier dictionary and per token mixing coefficients, replacing the ubiquitous self attention mechanism in…

Computation and Language · Computer Science 2025-05-02 Andrew Kiruluta

Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a…

Sound · Computer Science 2024-03-12 Roi Benita , Michael Elad , Joseph Keshet

This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-26 Pin-Jui Ku , Alexander H. Liu , Roman Korostik , Sung-Feng Huang , Szu-Wei Fu , Ante Jukić

Graph Contrastive Learning (GCL) has demonstrated remarkable effectiveness in learning representations on graphs in recent years. To generate ideal augmentation views, the augmentation generation methods should preserve essential…

Machine Learning · Computer Science 2024-09-06 Kaiqi Yang , Haoyu Han , Wei Jin , Hui Liu

Recently, variational autoencoder (VAE), a deep representation learning (DRL) model, has been used to perform speech enhancement (SE). However, to the best of our knowledge, current VAE-based SE methods only apply VAE to the model speech…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-25 Yang Xiang , Jesper Lisby Højvang , Morten Højfeldt Rasmussen , Mads Græsbøll Christensen

Complex multivariate time series arise in many fields, ranging from computer vision to robotics or medicine. Often we are interested in the independent underlying factors that give rise to the high-dimensional data we are observing. While…

Machine Learning · Statistics 2021-02-11 Simon Bing , Vincent Fortuin , Gunnar Rätsch

We study the problem of training a flow-based generative model, parametrized by a two-layer autoencoder, to sample from a high-dimensional Gaussian mixture. We provide a sharp end-to-end analysis of the problem. First, we provide a tight…

Machine Learning · Statistics 2024-08-20 Hugo Cui , Florent Krzakala , Eric Vanden-Eijnden , Lenka Zdeborová

Learning from an imbalanced distribution presents a major challenge in predictive modeling, as it generally leads to a reduction in the performance of standard algorithms. Various approaches exist to address this issue, but many of them…

Machine Learning · Computer Science 2024-12-11 Samuel Stocksieker , Denys Pommeret , Arthur Charpentier

We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias prompts from a few samples but also captures the distribution…

Computer Vision and Pattern Recognition · Computer Science 2022-05-09 Yuning Lu , Jianzhuang Liu , Yonggang Zhang , Yajing Liu , Xinmei Tian