相关论文: Optimal Transport Maps are Good Voice Converters

Optimal Transport has recently gained interest in machine learning for applications ranging from domain adaptation, sentence similarities to deep learning. Yet, its ability to capture frequently occurring structure beyond the "ground…

In the design of multitarget interplanetary missions, there are always many options available, making it often impractical to optimize in detail each transfer trajectory in a preliminary search phase. Fast and accurate estimation methods…

This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two…

This paper presents a multiscale approach to efficiently compute approximate optimal transport plans between point sets. It is particularly well-suited for point sets that are in high-dimensions, but are close to being intrinsically…

This paper presents a light-weight, high-quality texture synthesis algorithm that easily generalizes to other applications such as style transfer and texture mixing. We represent texture features through the deep neural activation vectors…

Consumer-grade music recordings such as those captured by mobile devices typically contain distortions in the form of background noise, reverb, and microphone-induced EQ. This paper presents a deep learning approach to enhance low-quality…

We develop a statistical inference method for an optimal transport map between distributions on real numbers with uniform confidence bands. The concept of optimal transport (OT) is used to measure distances between distributions, and OT…

Generative models such as Variational Auto Encoders (VAEs) and Generative Adversarial Networks (GANs) are typically trained for a fixed prior distribution in the latent space, such as uniform or Gaussian. After a trained model is obtained,…

Large Language Models (LLMs) have become an indispensable part of natural language processing tasks. However, autoregressive sampling has become an efficiency bottleneck. Multi-Draft Speculative Decoding (MDSD) is a recent approach where,…

Due to the mismatch of statistical distributions of acoustic speech between training and testing sets, the performance of spoken language identification (SLID) could be drastically degraded. In this paper, we propose an unsupervised neural…

Automatic tagging of music is an important research topic in Music Information Retrieval and audio analysis algorithms proposed for this task have achieved improvements with advances in deep learning. In particular, many state-of-the-art…

In speech synthesis and speech enhancement systems, melspectrograms need to be precise in acoustic representations. However, the generated spectrograms are over-smooth, that could not produce high quality synthesized speech. Inspired by…

Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream task, without sacrificing performance and…

Neural language models are often trained with maximum likelihood estimation (MLE), where the next word is generated conditioned on the ground-truth word tokens. During testing, however, the model is instead conditioned on previously…

We introduce a formulation of optimal transport problem for distributions on function spaces, where the stochastic map between functional domains can be partially represented in terms of an (infinite-dimensional) Hilbert-Schmidt operator…

Turn-taking management is crucial for any social interaction. Still, it is challenging to model human-machine interaction due to the complexity of the social context and its multimodal nature. Unlike conventional systems based on silence…

Recent advances in large-scale optimal transport have greatly extended its application scenarios in machine learning. However, existing methods either not explicitly learn the transport map or do not support general cost function. In this…

While mel-spectrograms have been widely utilized as intermediate representations in zero-shot text-to-speech (TTS), their inherent redundancy leads to inefficiency in learning text-speech alignment. Compact VAE-based latent representations…

The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether one can find the optimal vocabulary without trial training. To answer these questions, we…

We present a novel approach for generating an artificial audio signal that interpolates between given source and target sounds. Our approach relies on the computation of Wasserstein barycenters of the source and target spectrograms,…