English
Related papers

Related papers: CLN-VC: Text-Free Voice Conversion Based on Fine-G…

200 papers

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…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-06 Yuying Xie , Michael Kuhlmann , Frederik Rautenberg , Zheng-Hua Tan , Reinhold Haeb-Umbach

Embedding paralinguistic properties is a challenging task as there are only a few hours of training data available for domains such as emotional speech. One solution to this problem is to pretrain a general self-supervised speech…

Computation and Language · Computer Science 2022-11-04 Florian Lux , Ching-Yi Chen , Ngoc Thang Vu

Machine unlearning aims to eliminate the influence of a subset of training samples (i.e., unlearning samples) from a trained model. Effectively and efficiently removing the unlearning samples without negatively impacting the overall model…

Machine Learning · Computer Science 2024-01-22 Hong kyu Lee , Qiuchen Zhang , Carl Yang , Jian Lou , Li Xiong

Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals contain not only speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-26 Youzhi Tu , Man-Wai Mak , Jen-Tzung Chien

As one of the most effective self-supervised representation learning methods, contrastive learning (CL) relies on multiple negative pairs to contrast against each positive pair. In the standard practice of contrastive learning, data…

Machine Learning · Computer Science 2024-01-18 Lu Wang , Chao Du , Pu Zhao , Chuan Luo , Zhangchi Zhu , Bo Qiao , Wei Zhang , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang , Qi Zhang

Voice conversion (VC) is a task that transforms voice from target audio to source without losing linguistic contents, it is challenging especially when source and target speakers are unseen during training (zero-shot VC). Previous…

Sound · Computer Science 2021-04-14 Shijun Wang , Damian Borth

Environmental Sound Classification (ESC) is a challenging field of research in non-speech audio processing. Most of current research in ESC focuses on designing deep models with special architectures tailored for specific audio datasets,…

Sound · Computer Science 2021-03-03 Alireza Nasiri , Jianjun Hu

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…

Sound · Computer Science 2024-09-05 Yan Rong , Li Liu

As a foundational technology for intelligent human-computer interaction, voice conversion (VC) seeks to transform speech from any source timbre into any target timbre. Traditional voice conversion methods based on Generative Adversarial…

Sound · Computer Science 2025-06-11 Wenhan Yao , Fen Xiao , Xiarun Chen , Jia Liu , YongQiang He , Weiping Wen

Large language models (LLMs) excel in natural language processing but adapting these LLMs to speech processing tasks efficiently is not straightforward. Direct task-specific fine-tuning is limited by overfitting risks, data requirements,…

Computation and Language · Computer Science 2025-06-02 Maike Züfle , Jan Niehues

Contrastive learning has shown remarkable success in the field of multimodal representation learning. In this paper, we propose a pipeline of contrastive language-audio pretraining to develop an audio representation by combining audio data…

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

Non-parallel voice conversion aims to convert voice from a source domain to a target domain without paired training data. Cycle-Consistent Generative Adversarial Networks (CycleGAN) and Variational Autoencoders (VAE) have been used for this…

Sound · Computer Science 2025-10-16 Maharnab Saikia

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

Vision-Language Models (VLMs) are essential for multimodal tasks, especially compositional reasoning (CR) tasks, which require distinguishing fine-grained semantic differences between visual and textual embeddings. However, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Xin Huang , Ruibin Li , Tong Jia , Wei Zheng , Ya Wang

Recent advances in unsupervised representation learning often rely on knowing the number of classes to improve feature extraction and clustering. However, this assumption raises an important question: is the number of classes always…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Houwang Jiang , Zhuxian Liu , Guodong Liu , Xiaolong Liu , Shihua Zhan

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this…

Computation and Language · Computer Science 2023-01-26 Xiang Chen , Xin Xie , Zhen Bi , Hongbin Ye , Shumin Deng , Ningyu Zhang , Huajun Chen

Learning with noisy labels (LNL) aims to ensure model generalization given a label-corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine-grained datasets (LNL-FG), which is more practical and…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Qi Wei , Lei Feng , Haoliang Sun , Ren Wang , Chenhui Guo , Yilong Yin

Voice conversion (VC) aims to modify the speaker's identity while preserving the linguistic content. Commonly, VC methods use an encoder-decoder architecture, where disentangling the speaker's identity from linguistic information is…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-19 Philip H. Lee , Ismail Rasim Ulgen , Berrak Sisman

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…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-07 Michael Kuhlmann , Fritz Seebauer , Janek Ebbers , Petra Wagner , Reinhold Haeb-Umbach