English
Related papers

Related papers: StarGANv2-VC: A Diverse, Unsupervised, Non-paralle…

200 papers

Recently, voice conversion (VC) without parallel data has been successfully adapted to multi-target scenario in which a single model is trained to convert the input voice to many different speakers. However, such model suffers from the…

Machine Learning · Computer Science 2019-08-23 Ju-chieh Chou , Cheng-chieh Yeh , Hung-yi Lee

Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence during training, while diffusion methods require multi-step…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-10 Zengwei Yao , Wei Kang , Han Zhu , Liyong Guo , Lingxuan Ye , Fangjun Kuang , Weiji Zhuang , Zhaoqing Li , Zhifeng Han , Long Lin , Daniel Povey

Voice Conversion (VC) is a technique that aims to transform the non-linguistic information of a source utterance to change the perceived identity of the speaker. While there is a rich literature on VC, most proposed methods are trained and…

Traditional voice conversion (VC) methods typically attempt to separate speaker identity and linguistic information into distinct representations, which are then combined to reconstruct the audio. However, effectively disentangling these…

Sound · Computer Science 2025-10-13 Huu Tuong Tu , Huan Vu , cuong tien nguyen , Dien Hy Ngo , Nguyen Thi Thu Trang

After demonstrating significant success in image synthesis, Generative Adversarial Network (GAN) models have likewise made significant progress in the field of speech synthesis, leveraging their capacity to adapt the precise distribution of…

Sound · Computer Science 2025-04-21 Sandipan Dhar , Md. Tousin Akhter , Nanda Dulal Jana , Swagatam Das

In this paper, we propose an enhanced triplet method that improves the encoding process of embeddings by jointly utilizing generative adversarial mechanism and multitasking optimization. We extend our triplet encoder with Generative…

Sound · Computer Science 2018-03-28 Wenhao Ding , Liang He

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

An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-09 Wen-Chin Huang , Hao Luo , Hsin-Te Hwang , Chen-Chou Lo , Yu-Huai Peng , Yu Tsao , Hsin-Min Wang

Emotional voice conversion aims to transform emotional prosody in speech while preserving the linguistic content and speaker identity. Prior studies show that it is possible to disentangle emotional prosody using an encoder-decoder network…

Sound · Computer Science 2021-02-12 Kun Zhou , Berrak Sisman , Rui Liu , Haizhou Li

This paper introduces a new framework for non-parallel emotion conversion in speech. Our framework is based on two key contributions. First, we propose a stochastic version of the popular CycleGAN model. Our modified loss function…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-10 Ravi Shankar , Hsi-Wei Hsieh , Nicolas Charon , Archana Venkataraman

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

We propose a unified approach to data-driven source-filter modeling using a single neural network for developing a neural vocoder capable of generating high-quality synthetic speech waveforms while retaining flexibility of the source-filter…

Sound · Computer Science 2021-06-29 Reo Yoneyama , Yi-Chiao Wu , Tomoki Toda

As a combination of visual and audio signals, video is inherently multi-modal. However, existing video generation methods are primarily intended for the synthesis of visual frames, whereas audio signals in realistic videos are disregarded.…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Jiawei Liu , Weining Wang , Sihan Chen , Xinxin Zhu , Jing Liu

We propose a novel training algorithm for a multi-speaker neural text-to-speech (TTS) model based on multi-task adversarial training. A conventional generative adversarial network (GAN)-based training algorithm significantly improves the…

Sound · Computer Science 2022-09-27 Yusuke Nakai , Yuki Saito , Kenta Udagawa , Hiroshi Saruwatari

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

Current methods for image-to-image translation produce compelling results, however, the applied transformation is difficult to control, since existing mechanisms are often limited and non-intuitive. We propose ParGAN, a generalization of…

Computer Vision and Pattern Recognition · Computer Science 2022-11-10 Diego Martin Arroyo , Alessio Tonioni , Federico Tombari

The problem of audio synthesis has been increasingly solved using deep neural networks. With the introduction of Generative Adversarial Networks (GAN), another efficient and adjective path has opened up to solve this problem. In this paper,…

Sound · Computer Science 2021-02-23 Shreeviknesh Sankaran , Sukavanan Nanjundan , G. Paavai Anand

Generative adversarial networks (GANs) are one of the most widely used generative models. GANs can learn complex multi-modal distributions, and generate real-like samples. Despite the major success of GANs in generating synthetic data, they…

Machine Learning · Computer Science 2021-09-07 Sanaz Mohammadjafari , Mucahit Cevik , Ayse Basar

Cross-lingual voice conversion (VC) is a task that aims to synthesize target voices with the same content while source and target speakers speak in different languages. Its challenge lies in the fact that the source and target data are…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-01 Che-Jui Chang

We propose a neural network for zero-shot voice conversion (VC) without any parallel or transcribed data. Our approach uses pre-trained models for automatic speech recognition (ASR) and speaker embedding, obtained from a speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Yurii Rebryk , Stanislav Beliaev