Tootfinder

Pureformer-VC: Non-parallel Voice Conversion with Pure Stylized Transformer Blocks and Triplet Discriminative Training
Wenhan Yao, Fen Xiao, Xiarun Chen, Jia Liu, YongQiang He, Weiping Wen
https://arxiv.org/abs/2506.08348

Pureformer-VC: Non-parallel Voice Conversion with Pure Stylized Transformer Blocks and Triplet Discriminative Training
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 Networks (GANs) encounter significant challenges in precisely encoding diverse speech elements and effectively synthesising these elements into natural-sounding converted speech. To overcome these limitations, we introduce Pureformer-VC, an encoder-decoder frame…

Turnkey, which builds low-level infrastructure for digital wallets used to store and manage crypto, raised a $30M Series B led by Bain Capital Crypto (Ben Weiss/Fortune)
https://fortune.com/crypto/2025/06/09/exclus…

Exclusive: Coinbase vets raise $30 million for crypto wallet startup Turnkey
The fundraise attracted big VC names like Bain Capital Crypto, Sequoia Capital and Lightspeed Faction.

Metacurity is pleased to offer our free and premium subscribers a weekly digest of the best long-form (and longish) infosec-related pieces we couldn't properly fit into our daily news crush.
This week's selection covers
--Bashar al-Assad was toppled by spyware,
--Facial recognition threatens us all with deportation,
--VC money fuels worker surveillance,
--Will Trump launch offensive cyber ops on US networks?,
--The Pall Mall Process and commercial c…

Best infosec-related long reads for the week of 5/31/25
Bashar al-Assad was toppled by spyware, Facial recognition threatens us all with deportation, VC money fuels worker surveillance, Will Trump launch offensive cyber ops on US networks?, The Pall Mall Process and commercial cyber intrusions, Self-confidence leads to GenAI skepticism, more

Source: Chime's IPO is expected to price at ~$11B, down from its $25B private valuation in 2021; every VC-backed IPO in the past 12 months has been a down round (Cory Weinberg/The Information)
https://www.theinformation.com/articles/every-vc-ba…

Every VC-Backed IPO in the Past 12 Months Has Been a Down Round
When banking app Chime goes public next month, it will mark the eighth straight venture capital–backed initial public offering in the past 12 months to be valued less than it was in private fundraising rounds. Chime, for instance, was valued at $25 billion in 2021, but its bankers have been ...

StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion
Fengjin Li, Jie Wang, Yadong Niu, Yongqing Wang, Meng Meng, Jian Luan, Zhiyong Wu
https://arxiv.org/abs/2506.02414

StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion
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 content. Since VC fundamentally involves disentangling speaker identity from linguistic content, leveraging structured semantic features could enhance conversion performance. However, previous attempts to incorporate semantic features into VC have shown limited eff…

PseudoVC: Improving One-shot Voice Conversion with Pseudo Paired Data
Songjun Cao, Qinghua Wu, Jie Chen, Jin Li, Long Ma
https://arxiv.org/abs/2506.01039 h…

PseudoVC: Improving One-shot Voice Conversion with Pseudo Paired Data
As parallel training data is scarce for one-shot voice conversion (VC) tasks, waveform reconstruction is typically performed by various VC systems. A typical one-shot VC system comprises a content encoder and a speaker encoder. However, two types of mismatches arise: one for the inputs to the content encoder during training and inference, and another for the inputs to the speaker encoder. To address these mismatches, we propose a novel VC training method called \textit{PseudoVC} in this paper. …

VC-dimension of generalized progressions in some nonabelian groups
Gabriel Conant, Aycin Iplikci Arodirik, Tora Ozawa, David Zeng
https://arxiv.org/abs/2505.21789

VC-dimension of generalized progressions in some nonabelian groups
We analyze generalized progressions in some nonabelian groups using a measure of complexity called VC-dimension, which was originally introduced in statistical learning theory by Vapnik and Chervonenkis. Here by a "generalized progression" in a group $G$, we mean a finite subset of $G$ built from a fixed set of generators in analogy to a (multidimensional) arithmetic progression of integers. These sets play an important role in additive combinatorics and, in particular, the study of approximate…

This https://arxiv.org/abs/2505.21568 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents
Voice cloning (VC)-resistant watermarking is an emerging technique for tracing and preventing unauthorized cloning. Existing methods effectively trace traditional VC models by training them on watermarked audio but fail in zero-shot VC scenarios, where models synthesize audio from an audio prompt without training. To address this, we propose VoiceMark, the first zero-shot VC-resistant watermarking method that leverages speaker-specific latents as the watermark carrier, allowing the watermark to…

Eu comentando num grupo "Caramba, o Flamengo estš ganhando de 5 a 0! E eu estava trabalhando aqui, nem lembrei que tinha jogo hoje."
A resposta do meu amigo: "Jš acabou. Mas agora que vc descobriu, o Juiz vai mandar voltar a bola pra um terceiro tempo e o Fortaleza vai virar pra 6 a 5!"
Sim, é esse o nível da minha fama de pé-frio rs.

ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization
Pengyu Ren, Wenhao Guan, Kaidi Wang, Peijie Chen, Qingyang Hong, Lin Li
https://arxiv.org/abs/2506.01032

ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization
In recent years, diffusion-based generative models have demonstrated remarkable performance in speech conversion, including Denoising Diffusion Probabilistic Models (DDPM) and others. However, the advantages of these models come at the cost of requiring a large number of sampling steps. This limitation hinders their practical application in real-world scenarios. In this paper, we introduce ReFlow-VC, a novel high-fidelity speech conversion method based on rectified flow. Specifically, ReFlow-VC…

This https://arxiv.org/abs/2302.11862 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Bounds on Functionality and Symmetric Difference -- Two Intriguing Graph Parameters
Functionality ($\mathrm{fun}$) is a graph parameter that generalizes graph degeneracy defined by Alecu et al. [JCTB, 2021]. They research the relation of functionality to many other graphs parameters (tree-width, clique-width, VC-dimension, etc.). Extending their research, we completely characterize the functionality of random graph $G(n,p)$ for all possible $p$. We provide matching (up to a constant factor) lower and upper bound for a large range of $p$. It follows from our bounds for $G(n,p)$…

Relativistic Deformation of Geometry through Function C(v): Scalar Deformation Flow and the Geometric Classification of 3-Manifolds
Anton Alexa
https://arxiv.org/abs/2506.01146

Relativistic Deformation of Geometry through Function C(v): Scalar Deformation Flow and the Geometric Classification of 3-Manifolds
We introduce the scalar deformation function C(v), which captures how local geometric structures respond to motion at velocity v. This function exhibits smooth analytic behavior and defines a critical velocity vc beyond which the geometry compresses. Extending C(v) into a flow C(v, tau), we construct a scalar analogue of Ricci flow that governs the evolution of geometric configurations toward symmetric, stable states without singularities. The flow is derived from a variational energy functiona…

Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching
Jialong Zuo, Shengpeng Ji, Minghui Fang, Mingze Li, Ziyue Jiang, Xize Cheng, Xiaoda Yang, Chen Feiyang, Xinyu Duan, Zhou Zhao
https://arxiv.org/abs/2506.01014

Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching
Zero-Shot Voice Conversion (VC) aims to transform the source speaker's timbre into an arbitrary unseen one while retaining speech content. Most prior work focuses on preserving the source's prosody, while fine-grained timbre information may leak through prosody, and transferring target prosody to synthesized speech is rarely studied. In light of this, we propose R-VC, a rhythm-controllable and efficient zero-shot voice conversion model. R-VC employs data perturbation techniques and discretize s…

Q&A with Mary Meeker on publishing her first Trends report since 2019, its focus on the AI revolution, why OpenAI may have an insurmountable lead, and more (Dan Primack/Axios)
https://www.axios.com/2025/05/30/mary-meeker-trends-report-openai

Q&A with Mary Meeker on the AI revolution
The famed internet analyst turned VC just published her first Trends report since 2019.