English
Related papers

Related papers: Improving the expressiveness of neural vocoding wi…

200 papers

Statistical signal processing based speech enhancement methods adopt expert knowledge to design the statistical models and linear filters, which is complementary to the deep neural network (DNN) based methods which are data-driven. In this…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-19 Wei Xue , Gang Quan , Chao Zhang , Guohong Ding , Xiaodong He , Bowen Zhou

In this work, we investigate the use of normalizing flows to model conditional distributions. In particular, we use our proposed method to analyze inverse problems with invertible neural networks by maximizing the posterior likelihood. Our…

Machine Learning · Computer Science 2019-11-07 Zhisheng Xiao , Qing Yan , Yali Amit

For enhancement of noisy speech, a method of threshold determination based on modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of the noisy speech by exponential distribution is presented. A custom…

Audio and Speech Processing · Electrical Eng. & Systems 2018-02-19 Md Tauhidul Islam , Celia Shahnaz , Wei-Ping Zhu , M. Omair Ahmad

Although embedded vector representations of words offer impressive performance on many natural language processing (NLP) applications, the information of ordered input sequences is lost to some extent if only context-based samples are used…

Computation and Language · Computer Science 2020-02-18 Bin Wang , Fenxiao Chen , Angela Wang , C. -C. Jay Kuo

Normalizing Flows (NFs) are universal density estimators based on Neural Networks. However, this universality is limited: the density's support needs to be diffeomorphic to a Euclidean space. In this paper, we propose a novel method to…

Machine Learning · Computer Science 2022-02-02 Christian Horvat , Jean-Pascal Pfister

Proper regularization is crucial in inverse problems to achieve high-quality reconstruction, even with an ill-conditioned measurement system. This is particularly true for three-dimensional photoacoustic tomography, which is computationally…

Optimization and Control · Mathematics 2024-09-26 Chao Wang , Alexandre H. Thiery

There are two types of methods for non-autoregressive text-to-speech models to learn the one-to-many relationship between text and speech effectively. The first one is to use an advanced generative framework such as normalizing flow (NF).…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-28 Yoonhyung Lee , Jinhyeok Yang , Kyomin Jung

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

Sound · Computer Science 2022-11-24 Hung-Shin Lee , Pin-Yuan Chen , Yao-Fei Cheng , Yu Tsao , Hsin-Min Wang

Both reverberation and additive noises degrade the speech quality and intelligibility. Weighted prediction error (WPE) method performs well on the dereverberation but with limitations. First, WPE doesn't consider the influence of the…

Sound · Computer Science 2017-08-29 Hao Li , Xueliang Zhang , Hui Zhang , Guanglai Gao

We propose a novel neural waveform compression method to catalyze emerging speech semantic communications. By introducing nonlinear transform and variational modeling, we effectively capture the dependencies within speech frames and…

Sound · Computer Science 2022-12-14 Shengshi Yao , Zixuan Xiao , Sixian Wang , Jincheng Dai , Kai Niu , Ping Zhang

We propose a way to favorably employ neural networks in the field of non-destructive testing using Full Waveform Inversion (FWI). The presented methodology discretizes the unknown material distribution in the domain with a neural network…

Machine Learning · Computer Science 2023-12-04 Stefan Kollmannsberger , Divya Singh , Leon Herrmann

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-31 Bo Wu , Meng Yu , Lianwu Chen , Chao Weng , Dan Su , Dong Yu

We introduce a new regularization method for Artificial Neural Networks (ANNs) based on Kernel Flows (KFs). KFs were introduced as a method for kernel selection in regression/kriging based on the minimization of the loss of accuracy…

Machine Learning · Statistics 2021-08-25 Gene Ryan Yoo , Houman Owhadi

Recently, direct modeling of raw waveforms using deep neural networks has been widely studied for a number of tasks in audio domains. In speaker verification, however, utilization of raw waveforms is in its preliminary phase, requiring…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-18 Jee-weon Jung , Hee-Soo Heo , Ju-ho Kim , Hye-jin Shim , Ha-Jin Yu

We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…

Sound · Computer Science 2018-05-03 Han Zhao , Shuayb Zarar , Ivan Tashev , Chin-Hui Lee

Normalizing flows have emerged as an important family of deep neural networks for modelling complex probability distributions. In this note, we revisit their coupling and autoregressive transformation layers as probabilistic graphical…

Machine Learning · Computer Science 2020-06-05 Antoine Wehenkel , Gilles Louppe

Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. However, these flow-based models still require long training…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Janis Postels , Mengya Liu , Riccardo Spezialetti , Luc Van Gool , Federico Tombari

Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching…

Sound · Computer Science 2025-03-24 Tianze Luo , Xingchen Miao , Wenbo Duan

Full-waveform inversion (FWI) is an accurate imaging approach for modeling velocity structure by minimizing the misfit between recorded and predicted seismic waveforms. However, the strong non-linearity of FWI resulting from fitting…

Geophysics · Physics 2021-10-04 Weiqiang Zhu , Kailai Xu , Eric Darve , Biondo Biondi , Gregory C. Beroza

Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price…

Machine Learning · Computer Science 2025-06-05 Raj Ghugare , Benjamin Eysenbach