English
Related papers

Related papers: A Deep Generative Model of Speech Complex Spectrog…

200 papers

Score-based generative models (SGMs) have recently shown impressive results for difficult generative tasks such as the unconditional and conditional generation of natural images and audio signals. In this work, we extend these models to the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-08 Simon Welker , Julius Richter , Timo Gerkmann

This paper presents a deep neural network (DNN)-based phase reconstruction from amplitude spectrograms. In audio signal and speech processing, the amplitude spectrogram is often used for processing, and the corresponding phase spectrogram…

This paper proposes a new loss using short-time Fourier transform (STFT) spectra for the aim of training a high-performance neural speech waveform model that predicts raw continuous speech waveform samples directly. Not only amplitude…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-31 Shinji Takaki , Toru Nakashika , Xin Wang , Junichi Yamagishi

We propose a novel spectral generative model for image synthesis that departs radically from the common variational, adversarial, and diffusion paradigms. In our approach, images, after being flattened into one-dimensional signals, are…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Andrew Kiruluta

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

We address speech enhancement based on variational autoencoders, which involves learning a speech prior distribution in the time-frequency (TF) domain. A zero-mean complex-valued Gaussian distribution is usually assumed for the generative…

Sound · Computer Science 2023-10-27 Ali Golmakani , Mostafa Sadeghi , Xavier Alameda-Pineda , Romain Serizel

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

Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-05 Sean Vasquez , Mike Lewis

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

Sound · Computer Science 2019-04-03 Hyeong-Seok Choi , Jang-Hyun Kim , Jaesung Huh , Adrian Kim , Jung-Woo Ha , Kyogu Lee

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

Currently, most speech processing techniques use magnitude spectrograms as front-end and are therefore by default discarding part of the signal: the phase. In order to overcome this limitation, we propose an end-to-end learning method for…

Sound · Computer Science 2018-02-01 Dario Rethage , Jordi Pons , Xavier Serra

This study investigates phase reconstruction for deep learning based monaural talker-independent speaker separation in the short-time Fourier transform (STFT) domain. The key observation is that, for a mixture of two sources, with their…

Sound · Computer Science 2018-11-26 Zhong-Qiu Wang , Ke Tan , DeLiang Wang

Deep generative models such as diffusion and flow matching are powerful machine learning tools capable of learning and sampling from high-dimensional distributions. They are particularly useful when the training data appears to be…

High Energy Physics - Phenomenology · Physics 2026-04-30 Zachary Bogorad , Ibrahim Elsharkawy , Yonatan Kahn , Andrew J. Larkoski , Noam Levi

This work builds on a previous work on unsupervised speech enhancement using a dynamical variational autoencoder (DVAE) as the clean speech model and non-negative matrix factorization (NMF) as the noise model. We propose to replace the NMF…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-14 Xiaoyu Lin , Simon Leglaive , Laurent Girin , Xavier Alameda-Pineda

We learn audio representations by solving a novel self-supervised learning task, which consists of predicting the phase of the short-time Fourier transform from its magnitude. A convolutional encoder is used to map the magnitude spectrum of…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Félix de Chaumont Quitry , Marco Tagliasacchi , Dominik Roblek

The Fourier transform, an explicit decomposition method for visual signals, has been employed to explain the out-of-distribution generalization behaviors of Deep Neural Networks (DNNs). Previous studies indicate that the amplitude spectrum…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Chengming Hu , Yeqian Du , Rui Wang , Hao Chen , Congcong Zhu

Traditional speech enhancement techniques modify the magnitude of a speech in time-frequency domain, and use the phase of a noisy speech to resynthesize a time domain speech. This work proposes a complex-valued Gaussian process latent…

Sound · Computer Science 2017-01-02 Sih-Huei Chen , Yuan-Shan Lee , Jia-Ching Wang

In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks. By splitting up the speech denoising task into non-overlapping subproblems and introducing a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-11 Aswin Sivaraman , Minje Kim

In this work, we propose a novel consistency-preserving loss function for recovering the phase information in the context of phase reconstruction (PR) and speech enhancement (SE). Different from conventional techniques that directly…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Pin-Jui Ku , Chun-Wei Ho , Hao Yen , Sabato Marco Siniscalchi , Chin-Hui Lee

Speech enhancement in hearing aids remains a difficult task in nonstationary acoustic environments, mainly because current signal processing algorithms rely on fixed, manually tuned parameters that cannot adapt in situ to different users or…

‹ Prev 1 2 3 10 Next ›