Searcharxiv⌕ Search

arXiv subjects

Avni Jain

Publications and source records attributed to Avni Jain.

8 recordsLinked to original sources
arXiv2025

Textless and Non-Parallel Speech-to-Speech Emotion Style Transfer

Given a pair of source and reference speech recordings, speech-to-speech (S2S) emotion style transfer involves the generation of an output speech that mimics the emotion characteristics of the reference while preserving the content and speaker attributes of the source. In this paper, we propose a speech-to-speech zero-shot emotion style transfer framework, termed S2S Zero-shot Emotion Style Transfer (S2S-ZEST), that enables the transfer of emotional attributes from the reference to the source while retaining the speaker identity and speech content. The S2S-ZEST framework consists of an analysis-synthesis pipeline in which the analysis module extracts semantic tokens, speaker representations, and emotion embeddings from speech. Using these representations, a pitch contour estimator and a duration predictor are learned. Further, a synthesis module is designed to generate speech based on the input representations and the derived factors. The analysis-synthesis pipeline is trained using an auto-encoding objective to enable efficient resynthesis during inference. For S2S emotion style transfer, the emotion embedding extracted from the reference speech along with the remaining representations from the source speech are used in the synthesis module to generate the style-transferred speech. In our experiments, we evaluate the converted speech on content and speaker preservation (with respect to the source) as well as on the effectiveness of the emotion style transfer (with respect to the reference). The proposed framework demonstrates improved emotion style transfer performance over prior methods in a textless and non-parallel setting. We also illustrate the application of the proposed work for data augmentation in emotion recognition tasks.

eess.AS↗
arXiv2015

Local structure-mobility relationships of confined fluids reverse upon supercooling

We examine the structural and dynamic properties of confined binary hard-sphere mixtures designed to mimic realizable colloidal thin films. Using computer simulations, governed by either Newtonian or overdamped Langevin dynamics, together with other techniques including a Fokker-Planck equation-based method, we measure the position-dependent and average diffusivities of particles along structurally isotropic and inhomogeneous dimensions of the fluids. At moderate packing fractions, local single-particle diffusivities normal to the direction of confinement are higher in regions of high total packing fraction; however, these trends are reversed as the film is supercooled at denser average packings. Auxiliary short-time measurements of particle displacements mirror data obtained for experimental supercooled colloidal systems. We find that average dynamics can be approximately predicted based on the distribution of available space for particle insertion across orders of magnitude in diffusivity regardless of the governing microscopic dynamics.

cond-mat.soft↗
arXiv2015

Tuning structure and mobility of solvation shells surrounding tracer additives

Molecular dynamics simulations and a stochastic Fokker-Planck equation based approach are used to illuminate how position-dependent solvent mobility near one or more tracer particle(s) is affected when tracer-solvent interactions are rationally modified to affect corresponding solvation structure. For tracers in a dense hard-sphere fluid, we compare two types of tracer-solvent interactions: (1) a hard-sphere-like interaction; and (2) a soft repulsion extending beyond the hard core designed via statistical mechanical theory to enhance tracer mobility at infinite dilution by suppressing coordination-shell structure (Carmer et al., Soft Matter 8 (2011)). For the latter case, we show that the mobility of surrounding solvent particles is also increased by addition of the soft repulsive interaction, which helps to rationalize the mechanism underlying the tracer's enhanced diffusivity. However, if multiple tracer surfaces are in closer proximity (as at higher tracer concentrations), similar interactions that disrupt local solvation structure instead suppress the position-dependent solvent dynamics.

cond-mat.stat-mech↗
arXiv2014

Dimensionality and design of isotropic interactions that stabilize honeycomb, square, simple cubic, and diamond lattices

We use inverse methods of statistical mechanics and computer simulations to investigate whether an isotropic interaction designed to stabilize a given two-dimensional (2D) lattice will also favor an analogous three-dimensional (3D) structure, and vice versa. Specifically, we determine the 3D ordered lattices favored by isotropic potentials optimized to exhibit stable 2D honeycomb (or square) periodic structures, as well as the 2D ordered structures favored by isotropic interactions designed to stabilize 3D diamond (or simple cubic) lattices. We find a remarkable `transferability' of isotropic potentials designed to stabilize analogous morphologies in 2D and 3D, irrespective of the exact interaction form, and we discuss the basis of this cross-dimensional behavior. Our results suggest that the discovery of interactions that drive assembly into certain 3D periodic structures of interest can be assisted by less computationally intensive optimizations targeting the analogous 2D lattices.

cond-mat.mtrl-sci↗
arXiv2014

Perspective: Inverse methods for material design

In this Perspective, we highlight several recent studies that illustrate how inverse strategies using appropriate physical models and computational methods can address complex materials design questions.

cond-mat.mtrl-sci↗
arXiv2013

Fine discretization of pair interactions and an approximate analytical strategy for predicting equilibrium behavior of complex fluids

We study whether fine discretization (i.e., terracing) of continuous pair interactions, when used in combination with first-order mean-spherical approximation theory, can lead to a simple and general analytical strategy for predicting the equilibrium structure and thermodynamics of complex fluids. Specifically, we implement a version of this approach to predict how screened electrostatic repulsions, solute-mediated depletion attractions, or ramp-shaped repulsions modify the radial distribution function and the potential energy of reference hard-sphere fluids, and we compare the predictions to exact results from molecular simulations.

cond-mat.soft↗
arXiv2013

Phase Behavior of Materials with Isotropic Interactions Designed by Inverse Strategies to Favor Diamond and Simple Cubic Lattice Ground States

We use molecular simulation to construct equilibrium phase diagrams for two recently introduced model materials with isotropic, soft-repulsive pair interactions designed to favor diamond and simple cubic lattice ground states, respectively, over a wide range of densities [Jain et al., Soft Matter 9 14 (2013)]. We employ free energy based Monte Carlo simulation techniques to precisely trace the inter-crystal and fluid-crystal coexistence curves. We find that both model materials display rich polymorphic phase behavior featuring stable crystals corresponding to the target ground-state structures, as well as a variety of other crystalline (e.g., hexagonal and body-centered cubic) phases and multiple reentrant melting transitions.

cond-mat.mtrl-sci↗