English
Related papers

Related papers: Towards Improved Zero-shot Voice Conversion with C…

200 papers

Variational auto-encoder (VAE) is an effective neural network architecture to disentangle a speech utterance into speaker identity and linguistic content latent embeddings, then generate an utterance for a target speaker from that of a…

Sound · Computer Science 2022-08-23 Ziang Long , Yunling Zheng , Meng Yu , Jack Xin

Expressive voice conversion aims to transfer both speaker identity and expressive attributes from a target speech to a given source speech. In this work, we improve over a self-supervised, non-autoregressive framework with a conditional…

Sound · Computer Science 2025-06-05 Seymanur Akti , Tuan Nam Nguyen , Alexander Waibel

In this work, we propose a zero-shot voice conversion method using speech representations trained with self-supervised learning. First, we develop a multi-task model to decompose a speech utterance into features such as linguistic content,…

Sound · Computer Science 2023-02-17 Shehzeen Hussain , Paarth Neekhara , Jocelyn Huang , Jason Li , Boris Ginsburg

Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn…

Machine Learning · Computer Science 2026-01-13 Ioannis Ziogas , Aamna Al Shehhi , Ahsan H. Khandoker , Leontios J. Hadjileontiadis

Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that…

Sound · Computer Science 2025-01-28 Qian Yang , Calbert Graham

Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data. Recently, self-supervised learning of speech representation…

Sound · Computer Science 2022-02-14 Trung Dang , Dung Tran , Peter Chin , Kazuhito Koishida

Disentangled representation learning aims to extract explanatory features or factors and retain salient information. Factorized hierarchical variational autoencoder (FHVAE) presents a way to disentangle a speech signal into sequential-level…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-06 Yuying Xie , Thomas Arildsen , Zheng-Hua Tan

We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e.g., videos and audios) under self-supervision. Specifically, we exploit the benefits of some readily accessible supervisory signals…

Computer Vision and Pattern Recognition · Computer Science 2020-05-26 Yizhe Zhu , Martin Renqiang Min , Asim Kadav , Hans Peter Graf

We study the problem of cross-lingual voice conversion in non-parallel speech corpora and one-shot learning setting. Most prior work require either parallel speech corpora or enough amount of training data from a target speaker. However, we…

Sound · Computer Science 2018-08-17 Seyed Hamidreza Mohammadi , Taehwan Kim

In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-12 Janek Ebbers , Michael Kuhlmann , Tobias Cord-Landwehr , Reinhold Haeb-Umbach

A fully disentangled variational auto-encoder (VAE) aims to identify disentangled latent components from observations. However, enforcing full independence between all latent components may be too strict for certain datasets. In some cases,…

Machine Learning · Computer Science 2025-02-05 Chengrui Li , Yunmiao Wang , Yule Wang , Weihan Li , Dieter Jaeger , Anqi Wu

Recently, audio-visual speech enhancement has been tackled in the unsupervised settings based on variational auto-encoders (VAEs), where during training only clean data is used to train a generative model for speech, which at test time is…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-09 Mostafa Sadeghi , Xavier Alameda-Pineda

Multimodal sensory data resembles the form of information perceived by humans for learning, and are easy to obtain in large quantities. Compared to unimodal data, synchronization of concepts between modalities in such data provides…

Machine Learning · Statistics 2018-05-30 Wei-Ning Hsu , James Glass

Currently, zero-shot voice conversion systems are capable of synthesizing the voice of unseen speakers. However, most existing approaches struggle to accurately replicate the speaking style of the source speaker or mimic the distinctive…

Sound · Computer Science 2025-06-02 Kaidi Wang , Wenhao Guan , Ziyue Jiang , Hukai Huang , Peijie Chen , Weijie Wu , Qingyang Hong , Lin Li

Style voice conversion aims to transform the speaking style of source speech into a desired style while keeping the original speaker's identity. However, previous style voice conversion approaches primarily focus on well-defined domains…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-09 Xinfa Zhu , Lei He , Yujia Xiao , Xi Wang , Xu Tan , Sheng Zhao , Lei Xie

Disentangled representations enable models to separate factors of variation that are shared across experimental conditions from those that are condition-specific. This separation is essential in domains such as biomedical data analysis,…

Machine Learning · Computer Science 2025-12-16 Yuli Slavutsky , Ozgur Beker , David Blei , Bianca Dumitrascu

In order to build language technologies for majority of the languages, it is important to leverage the resources available in public domain on the internet - commonly referred to as `Found Data'. However, such data is characterized by the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-27 Nishant Gurunath , Sai Krishna Rallabandi , Alan Black

An effective approach to non-parallel voice conversion (VC) is to utilize deep neural networks (DNNs), specifically variational auto encoders (VAEs), to model the latent structure of speech in an unsupervised manner. A previous study has…

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

Self-supervised disentangled representation learning is a critical task in sequence modeling. The learnt representations contribute to better model interpretability as well as the data generation, and improve the sample efficiency for…

Machine Learning · Computer Science 2021-10-26 Junwen Bai , Weiran Wang , Carla Gomes

Independent components within low-dimensional representations are essential inputs in several downstream tasks, and provide explanations over the observed data. Video-based disentangled factors of variation provide low-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2022-02-22 Juan F. Hernández Albarracín , Adín Ramírez Rivera