English
Related papers

Related papers: Discrete Unit based Masking for Improving Disentan…

200 papers

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…

Most of the prevalent approaches in speech prosody modeling rely on learning global style representations in a continuous latent space which encode and transfer the attributes of reference speech. However, recent work on neural codecs which…

Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully based on speaker labels. However, the performance of model…

Sound · Computer Science 2023-11-16 Yimin Deng , Xulong Zhang , Jianzong Wang , Ning Cheng , Jing Xiao

Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between different speakers using parallel data, which is expensive to…

The primary characteristic of robust speaker representations is that they are invariant to factors of variability not related to speaker identity. Disentanglement of speaker representations is one of the techniques used to improve…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-09 Raghuveer Peri , Haoqi Li , Krishna Somandepalli , Arindam Jati , Shrikanth Narayanan

This paper introduces a novel voice conversion (VC) model, guided by text instructions such as "articulate slowly with a deep tone" or "speak in a cheerful boyish voice". Unlike traditional methods that rely on reference utterances to…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-17 Chun-Yi Kuan , Chen An Li , Tsu-Yuan Hsu , Tse-Yang Lin , Ho-Lam Chung , Kai-Wei Chang , Shuo-yiin Chang , Hung-yi Lee

Voice Conversion (VC) modifies speech to match a target speaker while preserving linguistic content. Traditional methods usually extract speaker information directly from speech while neglecting the explicit utilization of linguistic…

Multimedia · Computer Science 2025-06-04 Fengjin Li , Jie Wang , Yadong Niu , Yongqing Wang , Meng Meng , Jian Luan , Zhiyong Wu

Diffusion-based generative models have exhibited powerful generative performance in recent years. However, as many attributes exist in the data distribution and owing to several limitations of sharing the model parameters across all levels…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 Ha-Yeong Choi , Sang-Hoon Lee , Seong-Whan Lee

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

Nowadays, recognition-synthesis-based methods have been quite popular with voice conversion (VC). By introducing linguistics features with good disentangling characters extracted from an automatic speech recognition (ASR) model, the VC…

Sound · Computer Science 2023-05-17 Xintao Zhao , Shuai Wang , Yang Chao , Zhiyong Wu , Helen Meng

The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-05 Arsha Nagrani , Joon Son Chung , Samuel Albanie , Andrew Zisserman

One-shot voice conversion (VC) with only a single target speaker's speech for reference has become a hot research topic. Existing works generally disentangle timbre, while information about pitch, rhythm and content is still mixed together.…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-24 SiCheng Yang , Methawee Tantrawenith , Haolin Zhuang , Zhiyong Wu , Aolan Sun , Jianzong Wang , Ning Cheng , Huaizhen Tang , Xintao Zhao , Jie Wang , Helen Meng

We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-26 Hui Lu , Disong Wang , Xixin Wu , Zhiyong Wu , Xunying Liu , Helen Meng

Recently, the standard variational autoencoder has been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. Variational autoencoders have then been conditioned on a label…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-04 Guillaume Carbajal , Julius Richter , Timo Gerkmann

This paper presents an experimental study on deep speaker embedding with an attention mechanism that has been found to be a powerful representation learning technique in speaker recognition. In this framework, an attention model works as a…

Sound · Computer Science 2018-09-26 Qiongqiong Wang , Koji Okabe , Kong Aik Lee , Hitoshi Yamamoto , Takafumi Koshinaka

High-quality speech corpora are essential foundations for most speech applications. However, such speech data are expensive and limited since they are collected in professional recording environments. In this work, we propose an…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-11 Haoyu Li , Yang Ai , Junichi Yamagishi

Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training. Unlike the majority of the research in VAE-VC which focuses on utilizing auxiliary losses or…

Sound · Computer Science 2021-12-07 Kei Akuzawa , Kotaro Onishi , Keisuke Takiguchi , Kohki Mametani , Koichiro Mori

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

We propose an approach to extract speaker embeddings that are robust to speaking style variations in text-independent speaker verification. Typically, speaker embedding extraction includes training a DNN for speaker classification and using…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-29 Amber Afshan , Abeer Alwan

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Sound · Computer Science 2019-07-03 Miquel India , Pooyan Safari , Javier Hernando