相关论文: Self-supervised learning for robust voice cloning

Pre-trained models are essential as feature extractors in modern machine learning systems in various domains. In this study, we hypothesize that representations effective for general audio tasks should provide multiple aspects of robust…

Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must either be closer in the representation space, or…

Voice cloning is the task of learning to synthesize the voice of an unseen speaker from a few samples. While current voice cloning methods achieve promising results in Text-to-Speech (TTS) synthesis for a new voice, these approaches lack…

Inspired by the recent progress in self-supervised learning for computer vision that generates supervision using data augmentations, we explore a new general-purpose audio representation learning approach. We propose learning…

Methods for extracting audio and speech features have been studied since pioneering work on spectrum analysis decades ago. Recent efforts are guided by the ambition to develop general-purpose audio representations. For example, deep neural…

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an…

In this work, we have worked towards two major goals. Firstly, we have investigated the importance of Batch Normalisation (BN) layers in a non-contrastive representation learning framework called Bootstrap Your Own Latent (BYOL). We…

In this work, we study self-supervised representation learning for 3D skeleton-based action recognition. We extend Bootstrap Your Own Latent (BYOL) for representation learning on skeleton sequence data and propose a new data augmentation…

Self-supervised learning (SSL) algorithms have emerged as powerful tools that can leverage large quantities of unlabeled audio data to pre-train robust representations that support strong performance on diverse downstream tasks. Up to now…

In this paper, we present a cross-lingual voice cloning approach. BN features obtained by SI-ASR model are used as a bridge across speakers and language boundaries. The relationships between text and BN features are modeled by the latent…

Voice cloning is a highly desired feature for personalized speech interfaces. Neural network based speech synthesis has been shown to generate high quality speech for a large number of speakers. In this paper, we introduce a neural voice…

Voice cloning is a prominent feature in personalized speech interfaces. A neural vocal cloning system can mimic someone's voice using just a few audio samples. Both speaker encoding and speaker adaptation are topics of research in the field…

Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image representation. From an augmented view of an image, BYOL trains an online network to predict a target network representation of a different augmented view of…

Learning representation from unlabeled time series data is a challenging problem. Most existing self-supervised and unsupervised approaches in the time-series domain do not capture low and high-frequency features at the same time. Further,…

Understanding model uncertainty is important for many applications. We propose Bootstrap Your Own Variance (BYOV), combining Bootstrap Your Own Latent (BYOL), a negative-free Self-Supervised Learning (SSL) algorithm, with Bayes by Backprop…

The cloning of a speaker's voice using an untranscribed reference sample is one of the great advances of modern neural text-to-speech (TTS) methods. Approaches for mimicking the prosody of a transcribed reference audio have also been…

Recently, few-shot voice cloning has achieved a significant improvement. However, most models for few-shot voice cloning are single-modal, and multi-modal few-shot voice cloning has been understudied. In this paper, we propose to use…

Voice cloning technologies have found applications in a variety of areas ranging from personalized speech interfaces to advertisement, robotics, and so on. Existing voice cloning systems are capable of learning speaker characteristics and…

One-shot voice cloning aims to transform speaker voice and speaking style in speech synthesized from a text-to-speech (TTS) system, where only a shot recording from the target reference speech can be used. Out-of-domain transfer is still a…

A text-to-speech (TTS) model trained to reconstruct speech given text tends towards predictions that are close to the average characteristics of a dataset, failing to model the variations that make human speech sound natural. This problem…