The imitation of voice, targeted on specific speech attributes such as timbre and speaking style, is crucial in speech generation. However, existing methods rely heavily on annotated data, and struggle with effectively disentangling timbre and style, leading to challenges in achieving controllable generation, especially in zero-shot scenarios. To address these issues, we propose Vevo, a versatile zero-shot voice imitation framework with controllable timbre and style. Vevo operates in two core stages: (1) Content-Style Modeling: Given either text or speech's content tokens as input, we utilize an autoregressive transformer to generate the content-style tokens, which is prompted by a style reference; (2) Acoustic Modeling: Given the content-style tokens as input, we employ a flow-matching transformer to produce acoustic representations, which is prompted by a timbre reference. To obtain the content and content-style tokens of speech, we design a fully self-supervised approach that progressively decouples the timbre, style, and linguistic content of speech. Specifically, we adopt VQ-VAE as the tokenizer for the continuous hidden features of HuBERT. We treat the vocabulary size of the VQ-VAE codebook as the information bottleneck, and adjust it carefully to obtain the disentangled speech representations. Solely self-supervised trained on 60K hours of audiobook speech data, without any fine-tuning on style-specific corpora, Vevo matches or surpasses existing methods in accent and emotion conversion tasks. Additionally, Vevo’s effectiveness in zero-shot voice conversion and text-to-speech tasks further demonstrates its strong generalization and versatility. Audio samples are available at https://versavoice.github.io/.

Density estimation is a building block for many other statistical methods, such as classification, nonparametric testing, and data compression. In this paper, we focus on a non-parametric approach to multivariate density estimation, and study its asymptotic properties under both frequentist and Bayesian settings. The estimated density function is obtained by considering a sequence of approximating spaces to the space of densities. These spaces consist of piecewise constant density functions supported by binary partitions with increasing complexity. To obtain an estimate, the partition is learned by maximizing either the likelihood of the corresponding histogram on that partition, or the marginal posterior probability of the partition under a suitable prior. We analyze the convergence rate of the maximum likelihood estimator and the posterior concentration rate of the Bayesian estimator, and conclude that for a relatively rich class of density functions the rate does not directly depend on the dimension. We also show that the Bayesian method can adapt to the unknown smoothness of the density function. The method is applied to several specific function classes and explicit rates are obtained. These include spatially sparse functions, functions of bounded variation, and Hölder continuous functions. We also introduce an ensemble approach, obtained by aggregating multiple density estimates fit under carefully designed perturbations, and show that for density functions lying in a Hölder space ($\mathcal{H}^{1, \beta}, 0 < \beta \leq 1$), the ensemble method can achieve minimax convergence rate up to a logarithmic term, while the corresponding rate of the density estimator based on a single partition is suboptimal for this function class.

We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework. Our method utilizes a background NNLM which models generic background text together with a collection of domain-specific entities modeled as individual FSTs. Each output token is generated by a mixture of these components; the mixture weights are estimated with a separately trained neural decider. We show that NFCLM significantly outperforms NNLM by 15.8% relative in terms of Word Error Rate. NFCLM achieves similar performance as traditional NNLM and FST shallow fusion while being less prone to overbiasing and 12 times more compact, making it more suitable for on-device usage.

We study a class of non-parametric density estimators under Bayesian settings. The estimators are obtained by adaptively partitioning the sample space. Under a suitable prior, we analyze the concentration rate of the posterior distribution, and demonstrate that the rate does not directly depend on the dimension of the problem in several special cases. Another advantage of this class of Bayesian density estimators is that it can adapt to the unknown smoothness of the true density function, thus achieving the optimal convergence rate without artificial conditions on the density. We also validate the theoretical results on a variety of simulated data sets.

Mass cytometry (CyTOF) has greatly expanded the capability of cytometry. It is now easy to generate multiple CyTOF samples in a single study, with each sample containing single-cell measurement on 50 markers for more than hundreds of thousands of cells. Current methods do not adequately address the issues concerning combining multiple samples for subpopulation discovery, and these issues can be quickly and dramatically amplified with increasing number of samples. To overcome this limitation, we developed Partition-Assisted Clustering and Multiple Alignments of Networks (PAC-MAN) for the fast automatic identification of cell populations in CyTOF data closely matching that of expert manual-discovery, and for alignments between subpopulations across samples to define dataset-level cellular states. PAC-MAN is computationally efficient, allowing the management of very large CyTOF datasets, which are increasingly common in clinical studies and cancer studies that monitor various tissue samples for each subject.

Given $iid$ observations from an unknown continuous distribution defined on some domain $\Omega$, we propose a nonparametric method to learn a piecewise constant function to approximate the underlying probability density function. Our density estimate is a piecewise constant function defined on a binary partition of $\Omega$. The key ingredient of the algorithm is to use discrepancy, a concept originates from Quasi Monte Carlo analysis, to control the partition process. The resulting algorithm is simple, efficient, and has provable convergence rate. We demonstrate empirically its efficiency as a density estimation method. We also show how it can be utilized to find good initializations for k-means.