English
Related papers

Related papers: CycleFlow: Leveraging Cycle Consistency in Flow Ma…

200 papers

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

Speaker verification aims to verify whether an input speech corresponds to the claimed speaker, and conventionally, this kind of system is deployed based on single-stream scenario, wherein the feature extractor operates in full frequency…

Sound · Computer Science 2025-09-03 Wei Yao , Shen Chen , Jiamin Cui , Yaolin Lou

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

Speech enhancement(SE) aims to recover clean speech from noisy recordings. Although generative approaches such as score matching and Schrodinger bridge have shown strong effectiveness, they are often computationally expensive. Flow matching…

Sound · Computer Science 2025-12-12 Liusha Yang , Ziru Ge , Gui Zhang , Junan Zhang , Zhizheng Wu

When large language models are fine-tuned to generate persona- or tone-conditioned responses, their output diversity is severely limited--a failure we term Cross-Style Collapse. We trace this collapse to the cross-entropy objective, which…

Computation and Language · Computer Science 2026-05-28 Kerui Peng , Feifei Li , Xingyu Fan , Wenhui Que

Zero-shot singing voice conversion (SVC) transforms a source singer's timbre to an unseen target speaker's voice while preserving melodic content without fine-tuning. Existing methods model speaker timbre and vocal content separately,…

Sound · Computer Science 2025-11-18 Bingsong Bai , Yizhong Geng , Fengping Wang , Cong Wang , Puyuan Guo , Yingming Gao , Ya Li

Flow matching (FM) is a family of training algorithms for fitting continuous normalizing flows (CNFs). Conditional flow matching (CFM) exploits the fact that the marginal vector field of a CNF can be learned by fitting least-squares…

Machine Learning · Statistics 2025-02-04 Ganchao Wei , Li Ma

Voice conversion (VC) transforms source speech into a target voice by preserving the content. However, timbre information from the source speaker is inherently embedded in the content representations, causing significant timbre leakage and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-30 Na Li , Chuke Wang , Yu Gu , Zhifeng Li

Singing Voice Conversion (SVC) aims to transform a source singing voice into a target singer while preserving lyrics and melody. Most existing SVC methods depend on F0 extractors to capture the lead melody from clean vocals. However, no…

Sound · Computer Science 2026-05-13 Chen Geng , Meng Chen , Ruohua Zhou , Ruolan Liu , Weifeng Zhao

Creating realistic and natural-sounding synthetic speech remains a big challenge for voice identities unseen during training. As there is growing interest in synthesizing voices of new speakers, here we investigate the ability of…

We present a formulation of flow matching as variational inference, which we refer to as variational flow matching (VFM). Based on this formulation we develop CatFlow, a flow matching method for categorical data. CatFlow is easy to…

Machine Learning · Computer Science 2025-08-19 Floor Eijkelboom , Grigory Bartosh , Christian Andersson Naesseth , Max Welling , Jan-Willem van de Meent

Recent language model (LM) advancements have showcased impressive zero-shot voice conversion (VC) performance. However, existing LM-based VC models usually apply offline conversion from source semantics to acoustic features, demanding the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-22 Zhichao Wang , Yuanzhe Chen , Xinsheng Wang , Lei Xie , Yuping Wang

Generating spoken dialogue is inherently more complex than monologue text-to-speech (TTS), as it demands both realistic turn-taking and the maintenance of distinct speaker timbres. While existing autoregressive (AR) models have made…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-15 Han Zhu , Wei Kang , Liyong Guo , Zengwei Yao , Fangjun Kuang , Weiji Zhuang , Zhaoqing Li , Zhifeng Han , Dong Zhang , Xin Zhang , Xingchen Song , Lingxuan Ye , Long Lin , Daniel Povey

This research project investigates the application of deep learning to timbre transfer, where the timbre of a source audio can be converted to the timbre of a target audio with minimal loss in quality. The adopted approach combines…

Sound · Computer Science 2021-10-12 Russell Sammut Bonnici , Charalampos Saitis , Martin Benning

Diffusion-based generative models have achieved state-of-the-art performance for perceptual quality in speech enhancement (SE). However, their iterative nature requires numerous Neural Function Evaluations (NFEs), posing a challenge for…

Given datasets from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain. Variants of this problem have been studied in many contexts, such as cross-domain translation and domain…

Machine Learning · Computer Science 2019-12-24 Aditya Grover , Christopher Chute , Rui Shu , Zhangjie Cao , Stefano Ermon

Recently, Flow Matching models have pushed the boundaries of high-fidelity data generation across a wide range of domains. It typically employs a single large network to learn the entire generative trajectory from noise to data. Despite…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Dogyun Park , Taehoon Lee , Minseok Joo , Hyunwoo J. Kim

This paper proposes a novel method, Explicit Flow Matching (ExFM), for training and analyzing flow-based generative models. ExFM leverages a theoretically grounded loss function, ExFM loss (a tractable form of Flow Matching (FM) loss), to…

Machine Learning · Computer Science 2024-07-03 Gleb Ryzhakov , Svetlana Pavlova , Egor Sevriugov , Ivan Oseledets

Inverse generation problems, such as denoising without ground truth observations, is a critical challenge in many scientific inquiries and real-world applications. While recent advances in generative models like diffusion models,…

Machine Learning · Computer Science 2025-02-18 Yuchen Zhang , Jian Zhou

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