English
Related papers

Related papers: WaveNODE: A Continuous Normalizing Flow for Speech…

200 papers

Today's generative neural networks allow the creation of high-quality synthetic speech at scale. While we welcome the creative use of this new technology, we must also recognize the risks. As synthetic speech is abused for monetary and…

Sound · Computer Science 2024-04-10 Konstantin Gasenzer , Moritz Wolter

In voice conversion (VC) applications, diffusion and flow-matching models have exhibited exceptional speech quality and speaker similarity performances. However, they are limited by slow conversion owing to their iterative inference.…

Sound · Computer Science 2026-02-23 Takuhiro Kaneko , Hirokazu Kameoka , Kou Tanaka , Yuto Kondo

This paper introduces WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis. WaveGrad 2 is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence. The model takes an…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-22 Nanxin Chen , Yu Zhang , Heiga Zen , Ron J. Weiss , Mohammad Norouzi , Najim Dehak , William Chan

Normalizing flows transform a simple base distribution into a complex target distribution and have proved to be powerful models for data generation and density estimation. In this work, we propose a novel type of normalizing flow driven by…

Machine Learning · Computer Science 2021-07-14 Ruizhi Deng , Bo Chang , Marcus A. Brubaker , Greg Mori , Andreas Lehrmann

A generative model based on a continuous-time normalizing flow between any pair of base and target probability densities is proposed. The velocity field of this flow is inferred from the probability current of a time-dependent density that…

Machine Learning · Computer Science 2023-03-10 Michael S. Albergo , Eric Vanden-Eijnden

Modeling and synthesizing image noise is an important aspect in many computer vision applications. The long-standing additive white Gaussian and heteroscedastic (signal-dependent) noise models widely used in the literature provide only a…

Computer Vision and Pattern Recognition · Computer Science 2019-08-23 Abdelrahman Abdelhamed , Marcus A. Brubaker , Michael S. Brown

This paper proposes an effective probability density distillation (PDD) algorithm for WaveNet-based parallel waveform generation (PWG) systems. Recently proposed teacher-student frameworks in the PWG system have successfully achieved a…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-29 Ryuichi Yamamoto , Eunwoo Song , Jae-Min Kim

State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Magnitude spectrum has been a dominant feature over the years.…

Sound · Computer Science 2015-10-08 Bo Fan , Siu Wa Lee , Xiaohai Tian , Lei Xie , Minghui Dong

Whispered-to-normal (W2N) speech conversion aims to reconstruct missing phonation from whispered input while preserving content and speaker identity. This task is challenging due to temporal misalignment between whisper and voiced…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-05 Fabian Ritter-Gutierrez , Md Asif Jalal , Pablo Peso Parada , Karthikeyan Saravanan , Yusun Shul , Minseung Kim , Gun-Woo Lee , Han-Gil Moon

Recently, neural vocoders have been widely used in speech synthesis tasks, including text-to-speech and voice conversion. However, when encountering data distribution mismatch between training and inference, neural vocoders trained on real…

Sound · Computer Science 2020-08-21 Po-chun Hsu , Chun-hsuan Wang , Andy T. Liu , Hung-yi Lee

Neural waveform models such as WaveNet have demonstrated better performance than conventional vocoders for statistical parametric speech synthesis. As an autoregressive (AR) model, WaveNet is limited by a slow sequential waveform generation…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-19 Xin Wang , Shinji Takaki , Junichi Yamagishi

Recently normalizing flows have been gaining traction in text-to-speech (TTS) and voice conversion (VC) due to their state-of-the-art (SOTA) performance. Normalizing flows are unsupervised generative models. In this paper, we introduce…

Sound · Computer Science 2023-12-29 Jakub Mosiński , Piotr Biliński , Thomas Merritt , Abdelhamid Ezzerg , Daniel Korzekwa

Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to training samples or VAE latents as data augmentation,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Qinyu Zhao , Guangting Zheng , Tao Yang , Rui Zhu , Xingjian Leng , Stephen Gould , Liang Zheng

The zero-shot scenario for speech generation aims at synthesizing a novel unseen voice with only one utterance of the target speaker. Although the challenges of adapting new voices in zero-shot scenario exist in both stages -- acoustic…

Sound · Computer Science 2022-07-06 Yi Lei , Shan Yang , Jian Cong , Lei Xie , Dan Su

Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues: 1) If the target distribution is manifold, due to the unmatch between the dimensions of the latent target distribution…

Machine Learning · Computer Science 2024-04-24 Qinglong Meng , Chongkun Xia , Xueqian Wang

Recent neural waveform synthesizers such as WaveNet, WaveGlow, and the neural-source-filter (NSF) model have shown good performance in speech synthesis despite their different methods of waveform generation. The similarity between speech…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-20 Yi Zhao , Xin Wang , Lauri Juvela , Junichi Yamagishi

The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer from their slow sequential inference process, while their…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-31 Lauri Juvela , Bajibabu Bollepalli , Junichi Yamagishi , Paavo Alku

Normalizing Flows (NFs) have been established as a principled framework for generative modeling. Standard NFs consist of a forward process and a reverse process: the forward process maps data to noise, while the reverse process generates…

Machine Learning · Computer Science 2025-12-12 Yiyang Lu , Qiao Sun , Xianbang Wang , Zhicheng Jiang , Hanhong Zhao , Kaiming He

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

Neural source-filter (NSF) models are deep neural networks that produce waveforms given input acoustic features. They use dilated-convolution-based neural filter modules to filter sine-based excitation for waveform generation, which is…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-28 Xin Wang , Junichi Yamagishi