English
Related papers

Related papers: Predictive-Generative Drift Decomposition for Spee…

200 papers

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Runhui Huang , Jianhua Han , Guansong Lu , Xiaodan Liang , Yihan Zeng , Wei Zhang , Hang Xu

In this paper we present a single-microphone speech enhancement algorithm. A hybrid approach is proposed merging the generative mixture of Gaussians (MoG) model and the discriminative neural network (NN). The proposed algorithm is executed…

Sound · Computer Science 2015-10-27 Shlomo E. Chazan , Jacob Goldberger , Sharon Gannot

Multi-channel speech enhancement aims to recover clean speech from noisy multi-channel recordings. Most deep learning methods employ discriminative training, which can lead to non-linear distortions from regression-based objectives,…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-26 Zhongweiyang Xu , Ashutosh Pandey , Juan Azcarreta , Zhaoheng Ni , Sanjeel Parekh , Buye Xu

Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing…

Machine Learning · Computer Science 2021-08-06 Vadim Popov , Ivan Vovk , Vladimir Gogoryan , Tasnima Sadekova , Mikhail Kudinov

Flow-based generative models are widely used in text-to-speech (TTS) systems to learn the distribution of audio features (e.g., Mel-spectrograms) given the input tokens and to sample from this distribution to generate diverse utterances.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-30 Sewade Ogun , Vincent Colotte , Emmanuel Vincent

Stochastic Interpolants (SI) is a powerful framework for generative modeling, capable of flexibly transforming between two probability distributions. However, its use in jointly optimized latent variable models remains unexplored as it…

Machine Learning · Computer Science 2026-04-23 Saurabh Singh , Dmitry Lagun

We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear systems. The drift of the generative SDE is $\hat b_t(x) = \nabla\phi(x)^\top\eta_t$, where…

Target speaker extraction (TSE) aims to recover the speech of a desired speaker from a mixture given a short enrollment utterance, while speech enhancement (SE) focuses on improving speech quality under noisy conditions. Most existing TSE…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-21 Bang Zeng , Beilong Tang , Wang Xiang , Ming Li

Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineering domains, clean data are often unavailable: instead, we only observe…

Machine Learning · Computer Science 2026-05-14 Chirag Modi , Jiequn Han , Eric Vanden-Eijnden , Joan Bruna

Diffusion-based generative models have recently achieved remarkable results in speech and vocal enhancement due to their ability to model complex speech data distributions. While these models generalize well to unseen acoustic environments,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-23 Yudong Yang , Zhan Liu , Wenyi Yu , Guangzhi Sun , Qiuqiang Kong , Chao Zhang

We propose Uni-ArrayDPS, a novel diffusion-based refinement framework for unified multi-channel speech enhancement and separation. Existing methods for multi-channel speech enhancement/separation are mostly discriminative and are highly…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-27 Zhongweiyang Xu , Ashutosh Pandey , Juan Azcarreta , Zhaoheng Ni , Sanjeel Parekh , Buye Xu , Romit Roy Choudhury

Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Lu Yu , Bartłomiej Twardowski , Xialei Liu , Luis Herranz , Kai Wang , Yongmei Cheng , Shangling Jui , Joost van de Weijer

Generative Universal Speech Enhancement (USE) methods aim to leverage generative models to improve speech quality under various types of distortions. However, existing generative speech enhancement methods often suffer from semantic…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-07 Xingchen Li , Hanke Xie , Ziqian Wang , Zihan Zhang , Longshuai Xiao , Shuai Wang , Lei Xie

Class-Incremental Learning (CIL) requires a model to continually learn new classes without forgetting old ones. A common and efficient solution freezes a pre-trained model and employs lightweight adapters, whose parameters are often forced…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Ruiqi Liu , Boyu Diao , Zijia An , Runjie Shao , Zhulin An , Fei Wang , Yongjun Xu

Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However, these methods may face challenges when generalising to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Berné Nortier , Mostafa Sadeghi , Romain Serizel

While recent text-to-speech (TTS) systems have made remarkable strides toward human-level quality, the performance of cross-lingual TTS lags behind that of intra-lingual TTS. This gap is mainly rooted from the speaker-language entanglement…

Sound · Computer Science 2023-06-13 Ji-Hoon Kim , Hong-Sun Yang , Yoon-Cheol Ju , Il-Hwan Kim , Byeong-Yeol Kim

The stochastic interpolant framework offers a powerful approach for constructing generative models based on ordinary differential equations (ODEs) or stochastic differential equations (SDEs) to transform arbitrary data distributions.…

Machine Learning · Computer Science 2025-07-29 Yuhao Liu , Yu Chen , Rui Hu , Longbo Huang

Auto encoding models have been extensively studied in recent years. They provide an efficient framework for sample generation, as well as for analysing feature learning. Furthermore, they are efficient in performing interpolations between…

Machine Learning · Statistics 2021-03-30 Adam Lindhe , Carl Ringqvist , Henrik Hult

Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various dense prediction tasks. However, dilated convolutions suffer from the gridding artifacts, which…

Computer Vision and Pattern Recognition · Computer Science 2019-05-03 Zhengyang Wang , Shuiwang Ji

Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…

Computation and Language · Computer Science 2025-09-03 Jialong Zuo , Guangyan Zhang , Minghui Fang , Shengpeng Ji , Xiaoqi Jiao , Jingyu Li , Yiwen Guo , Zhou Zhao