paper-with-me

홈 › Papers

Adversarially Trained Autoencoders for Parallel-Data-Free Voice Conversion

2019-05-09 · Orhan Ocal, Oguz H. Elibol, Gokce Keskin, Cory Stephenson, Anil Thomas, Kannan Ramchandran

We present a method for converting the voices between a set of speakers. Our method is based on training multiple autoencoder paths, where there is a single speaker-independent encoder and multiple speaker-dependent decoders. The autoencoders are trained with an addition of an adversarial loss which is provided by an auxiliary classifier in order to guide the output of the encoder to be speaker independent. The training of the model is unsupervised in the sense that it does not require collecting the same utterances from the speakers nor does it require time aligning over phonemes. Due to the use of a single encoder, our method can generalize to converting the voice of out-of-training speakers to speakers in the training dataset. We present subjective tests corroborating the performance of our method.

📄 PDF Abstract BibTeX arXiv:1905.03864

Code (0)

등록된 구현이 없습니다.

Tasks

Voice Conversion

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음
Auxiliary Classifier Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the…

Similar Papers 제목 키워드 기반

Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer

2020-10-02 · COLING 2020 8 · Yufang Huang, Wentao Zhu, Deyi Xiong, Yiye Zhang 외

Unsupervised text style transfer is full of challenges due to the lack of parallel data and difficulties in content preservation. In this paper, we propose a novel neural approach to unsupervised text style transfer, whi…

Style TransferText Style TransferUnsupervised Text Style Transfer

Adversarially Regularized Autoencoders

2017-06-13 · Jake Zhao, Yoon Kim, Kelly Zhang, Alexander M. Rush 외

Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to d…

Representation LearningStyle Transfer

Watermarking and Anomaly Detection in Machine Learning Models for LORA RF Fingerprinting

2025-09-18 · Aarushi Mahajan, Wayne Burleson arxiv

Radio frequency fingerprint identification (RFFI) distinguishes wireless devices by the small variations in their analog circuits, avoiding heavy cryptographic authentication. While deep learning on spectrograms improves…

Anomaly Detection

Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulations

2021-04-13 · César Quilodrán-Casas, Rossella Arcucci, Laetitia Mottet, Yike Guo 외

This paper presents an approach to improve the forecast of computational fluid dynamics (CFD) simulations of urban air pollution using deep learning, and most specifically adversarial training. This adversarial approach …

Time SeriesTime Series Analysis

Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification

2020-07-11 · ICLR 2021 1 · Francisco Utrera, Evan Kravitz, N. Benjamin Erichson, Rajiv Khanna 외

Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. This process consists of taking a neural network pre-trained on a large fea…

ClassificationGeneral Classificationimage-classificationImage Classification+1