中文
相关论文

相关论文: EAD-VC: Enhancing Speech Auto-Disentanglement for …

200 篇论文

Voice Conversion (VC) converts the voice of a source speech to that of a target while maintaining the source's content. Speech can be mainly decomposed into four components: content, timbre, rhythm and pitch. Unfortunately, most related…

声音 · 计算机科学 2023-06-22 Zhonghua Liu , Shijun Wang , Ning Chen

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.…

音频与语音处理 · 电气工程与系统科学 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

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

声音 · 计算机科学 2024-08-27 Zhaoxi Mu , Xinyu Yang , Sining Sun , Qing Yang

The information bottleneck auto-encoder is a tool for disentanglement commonly used for voice transformation. The successful disentanglement relies on the right choice of bottleneck size. Previous bottleneck auto-encoders created the…

音频与语音处理 · 电气工程与系统科学 2023-10-06 Frederik Bous , Axel Roebel

Disentangling speaker and content attributes of a speech signal into separate latent representations followed by decoding the content with an exchanged speaker representation is a popular approach for voice conversion, which can be trained…

音频与语音处理 · 电气工程与系统科学 2022-09-07 Michael Kuhlmann , Fritz Seebauer , Janek Ebbers , Petra Wagner , Reinhold Haeb-Umbach

Face-based Voice Conversion (FVC) is a novel task that leverages facial images to generate the target speaker's voice style. Previous work has two shortcomings: (1) suffering from obtaining facial embeddings that are well-aligned with the…

声音 · 计算机科学 2024-09-05 Yan Rong , Li Liu

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…

音频与语音处理 · 电气工程与系统科学 2023-11-02 Tianchi Liu , Kong Aik Lee , Qiongqiong Wang , Haizhou Li

Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features…

音频与语音处理 · 电气工程与系统科学 2022-10-13 Sung Hwan Mun , Min Hyun Han , Minchan Kim , Dongjune Lee , Nam Soo Kim

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that…

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…

音频与语音处理 · 电气工程与系统科学 2022-04-06 Yuying Xie , Thomas Arildsen , Zheng-Hua Tan

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio…

声音 · 计算机科学 2024-01-19 Yimin Deng , Huaizhen Tang , Xulong Zhang , Ning Cheng , Jing Xiao , Jianzong Wang

Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainability, and fairness…

音频与语音处理 · 电气工程与系统科学 2023-08-09 Michael Kuhlmann , Adrian Meise , Fritz Seebauer , Petra Wagner , Reinhold Haeb-Umbach

Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity…

声音 · 计算机科学 2022-08-09 Huaizhen Tang , Xulong Zhang , Jianzong Wang , Ning Cheng , Zhen Zeng , Edward Xiao , Jing Xiao

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…

声音 · 计算机科学 2025-01-28 Qian Yang , Calbert Graham

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…

音频与语音处理 · 电气工程与系统科学 2022-10-26 Hui Lu , Disong Wang , Xixin Wu , Zhiyong Wu , Xunying Liu , Helen Meng

Any-to-any voice conversion problem aims to convert voices for source and target speakers, which are out of the training data. Previous works wildly utilize the disentangle-based models. The disentangle-based model assumes the speech…

声音 · 计算机科学 2022-02-23 Qiqi Wang , Xulong Zhang , Jianzong Wang , Ning Cheng , Jing Xiao

Speech information can be roughly decomposed into four components: language content, timbre, pitch, and rhythm. Obtaining disentangled representations of these components is useful in many speech analysis and generation applications.…

音频与语音处理 · 电气工程与系统科学 2021-03-16 Kaizhi Qian , Yang Zhang , Shiyu Chang , David Cox , Mark Hasegawa-Johnson

Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in diverse fields such as natural language processing, computer…

机器学习 · 计算机科学 2023-02-06 John Harvill , Jarred Barber , Arun Nair , Ramin Pishehvar

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…

音频与语音处理 · 电气工程与系统科学 2022-01-04 Guillaume Carbajal , Julius Richter , Timo Gerkmann

Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…

音频与语音处理 · 电气工程与系统科学 2024-09-06 Yuying Xie , Michael Kuhlmann , Frederik Rautenberg , Zheng-Hua Tan , Reinhold Haeb-Umbach
‹ 上一页 1 2 3 10 下一页 ›