English
Related papers

Related papers: BigVGAN: A Universal Neural Vocoder with Large-Sca…

200 papers

Recently, BigVGAN has emerged as high-performance speech vocoder. Its sequence-to-sequence-based synthesis, however, prohibits usage in low-latency conversational applications. Our work addresses this shortcoming in three steps. First, we…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-27 Renzheng Shi , Andreas Bär , Marvin Sach , Wouter Tirry , Tim Fingscheidt

In a recent paper, we have presented a generative adversarial network (GAN)-based model for unconditional generation of the mel-spectrograms of singing voices. As the generator of the model is designed to take a variable-length sequence of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-13 Jen-Yu Liu , Yu-Hua Chen , Yin-Cheng Yeh , Yi-Hsuan Yang

We present a deep neural network based singing voice synthesizer, inspired by the Deep Convolutions Generative Adversarial Networks (DCGAN) architecture and optimized using the Wasserstein-GAN algorithm. We use vocoder parameters for…

Sound · Computer Science 2020-02-13 Pritish Chandna , Merlijn Blaauw , Jordi Bonada , Emilia Gomez

While generative adversarial networks (GANs) have been widely used in research on audio generation, the training of a GAN model is known to be unstable, time consuming, and data inefficient. Among the attempts to ameliorate the training…

Sound · Computer Science 2022-09-07 Yen-Tung Yeh , Bo-Yu Chen , Yi-Hsuan Yang

Several of the latest GAN-based vocoders show remarkable achievements, outperforming autoregressive and flow-based competitors in both qualitative and quantitative measures while synthesizing orders of magnitude faster. In this work, we…

Sound · Computer Science 2021-08-24 Jaeseong You , Dalhyun Kim , Gyuhyeon Nam , Geumbyeol Hwang , Gyeongsu Chae

GAN vocoders are currently one of the state-of-the-art methods for building high-quality neural waveform generative models. However, most of their architectures require dozens of billion floating-point operations per second (GFLOPS) to…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-03 Ahmed Mustafa , Jean-Marc Valin , Jan Büthe , Paris Smaragdis , Mike Goodwin

Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. Although such methods improve the sampling efficiency and memory usage, their sample quality has not yet reached that of…

Sound · Computer Science 2020-10-26 Jungil Kong , Jaehyeon Kim , Jaekyoung Bae

This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by…

Computation and Language · Computer Science 2017-11-07 Anuroop Sriram , Heewoo Jun , Yashesh Gaur , Sanjeev Satheesh

Diffusion-based audio and music generation models commonly perform generation by constructing an image representation of audio (e.g., a mel-spectrogram) and then convert it to audio using a phase reconstruction model or vocoder. Typical…

Sound · Computer Science 2024-10-08 Ge Zhu , Juan-Pablo Caceres , Zhiyao Duan , Nicholas J. Bryan

In recent years, generative adversarial networks (GANs) have made significant progress in generating audio sequences. However, these models typically rely on bandwidth-limited mel-spectrograms, which constrain the resolution of generated…

Sound · Computer Science 2025-05-15 Zeeshan Ahmad , Shudi Bao , Meng Chen

In this work, we propose a full-band real-time speech enhancement system with GAN-based stochastic regeneration. Predictive models focus on estimating the mean of the target distribution, whereas generative models aim to learn the full…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-30 Sanberk Serbest , Tijana Stojkovic , Milos Cernak , Andrew Harper

We propose Relativistic Adversarial Feedback (RAF), a novel training objective for GAN vocoders that improves in-domain fidelity and generalization to unseen scenarios. Although modern GAN vocoders employ advanced architectures, their…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-13 Yongjoon Lee , Jung-Woo Choi

Recent improvements in Generative Adversarial Neural Networks (GANs) have shown their ability to generate higher quality samples as well as to learn good representations for transfer learning. Most of the representation learning methods…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-02 Kazi Nazmul Haque , Rajib Rana , John H. L. Hansen , Björn Schuller

Denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) are popular generative models for neural vocoders. The DDPMs and GANs can be characterized by the iterative denoising framework and adversarial…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-04 Yuma Koizumi , Kohei Yatabe , Heiga Zen , Michiel Bacchiani

This paper introduces a unified source-filter network with a harmonic-plus-noise source excitation generation mechanism. In our previous work, we proposed unified Source-Filter GAN (uSFGAN) for developing a high-fidelity neural vocoder with…

Sound · Computer Science 2022-07-04 Reo Yoneyama , Yi-Chiao Wu , Tomoki Toda

A generative adversarial network (GAN)-based vocoder trained with an adversarial discriminator is commonly used for speech synthesis because of its fast, lightweight, and high-quality characteristics. However, this data-driven model…

Sound · Computer Science 2024-03-26 Takuhiro Kaneko , Hirokazu Kameoka , Kou Tanaka

Separating two sources from an audio mixture is an important task with many applications. It is a challenging problem since only one signal channel is available for analysis. In this paper, we propose a novel framework for singing voice…

Sound · Computer Science 2017-11-15 Zhe-Cheng Fan , Yen-Lin Lai , Jyh-Shing Roger Jang

Although recent works on neural vocoder have improved the quality of synthesized audio, there still exists a gap between generated and ground-truth audio in frequency space. This difference leads to spectral artifacts such as hissing noise…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-15 Ji-Hoon Kim , Sang-Hoon Lee , Ji-Hyun Lee , Seong-Whan Lee

In current two-stage neural text-to-speech (TTS) paradigm, it is ideal to have a universal neural vocoder, once trained, which is robust to imperfect mel-spectrogram predicted from the acoustic model. To this end, we propose Robust MelGAN…

Sound · Computer Science 2022-11-03 Kun Song , Jian Cong , Xinsheng Wang , Yongmao Zhang , Lei Xie , Ning Jiang , Haiying Wu

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