English
Related papers

Related papers: DSPGAN: a GAN-based universal vocoder for high-fid…

200 papers

Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms. Such vocoding procedures create a computational bottleneck…

Sound · Computer Science 2019-07-29 Paarth Neekhara , Chris Donahue , Miller Puckette , Shlomo Dubnov , Julian McAuley

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

Our previous work, the unified source-filter GAN (uSFGAN) vocoder, introduced a novel architecture based on the source-filter theory into the parallel waveform generative adversarial network to achieve high voice quality and pitch…

Sound · Computer Science 2023-02-28 Reo Yoneyama , Yi-Chiao Wu , Tomoki Toda

Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-02 Ahmed Mustafa , Arijit Biswas , Christian Bergler , Julia Schottenhamml , Andreas Maier

Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which are convenient for…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-27 Lauri Juvela , Bajibabu Bollepalli , Junichi Yamagishi , Paavo Alku

Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality…

Audio and Speech Processing · Electrical Eng. & Systems 2019-12-10 Kundan Kumar , Rithesh Kumar , Thibault de Boissiere , Lucas Gestin , Wei Zhen Teoh , Jose Sotelo , Alexandre de Brebisson , Yoshua Bengio , Aaron Courville

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

Automatic Speaker Verification (ASV) technology has become commonplace in virtual assistants. However, its performance suffers when there is a mismatch between the train and test domains. Mixed bandwidth training, i.e., pooling training…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-07 Saurabh Kataria , Jesús Villalba , Laureano Moro-Velázquez , Piotr Żelasko , Najim Dehak

Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech…

Sound · Computer Science 2023-12-19 Chunyu Qiang , Hao Li , Yixin Tian , Yi Zhao , Ying Zhang , Longbiao Wang , Jianwu Dang

Generative adversarial network (GAN)-based vocoders have been intensively studied because they can synthesize high-fidelity audio waveforms faster than real-time. However, it has been reported that most GANs fail to obtain the optimal…

Sound · Computer Science 2024-03-26 Takashi Shibuya , Yuhta Takida , Yuki Mitsufuji

Voice conversion is a method that allows for the transformation of speaking style while maintaining the integrity of linguistic information. There are many researchers using deep generative models for voice conversion tasks. Generative…

Sound · Computer Science 2023-08-29 Xulong Zhang , Jianzong Wang , Ning Cheng , Jing Xiao

High-fidelity singing voices usually require higher sampling rate (e.g., 48kHz) to convey expression and emotion. However, higher sampling rate causes the wider frequency band and longer waveform sequences and throws challenges for singing…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-04 Jiawei Chen , Xu Tan , Jian Luan , Tao Qin , Tie-Yan Liu

This paper presents a speaking-rate-controllable HiFi-GAN neural vocoder. Original HiFi-GAN is a high-fidelity, computationally efficient, and tiny-footprint neural vocoder. We attempt to incorporate a speaking rate control function into…

Sound · Computer Science 2022-04-25 Detai Xin , Shinnosuke Takamichi , Takuma Okamoto , Hisashi Kawai , Hiroshi Saruwatari

Neural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while generating high-quality speech waveforms. Since the perceptually important…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-04 Taejun Bak , Junmo Lee , Hanbin Bae , Jinhyeok Yang , Jae-Sung Bae , Young-Sun Joo

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

Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-23 Jian Cong , Shan Yang , Lei Xie , Dan Su

GAN-based neural vocoders, such as Parallel WaveGAN and MelGAN have attracted great interest due to their lightweight and parallel structures, enabling them to generate high fidelity waveform in a real-time manner. In this paper, inspired…

Sound · Computer Science 2021-03-30 Congyi Wang , Yu Chen , Bin Wang , Yi Shi

Most state-of-the-art Text-to-Speech systems use the mel-spectrogram as an intermediate representation, to decompose the task into acoustic modelling and waveform generation. A mel-spectrogram is extracted from the waveform by a simple,…

A method for statistical parametric speech synthesis incorporating generative adversarial networks (GANs) is proposed. Although powerful deep neural networks (DNNs) techniques can be applied to artificially synthesize speech waveform, the…

Sound · Computer Science 2017-09-26 Yuki Saito , Shinnosuke Takamichi , Hiroshi Saruwatari

Neural vocoders model the raw audio waveform and synthesize high-quality audio, but even the highly efficient ones, like MB-MelGAN and LPCNet, fail to run real-time on a low-end device like a smartglass. A pure digital signal processing…

Sound · Computer Science 2024-01-22 Prabhav Agrawal , Thilo Koehler , Zhiping Xiu , Prashant Serai , Qing He