paper-with-me

Papers

Face Reconstruction from Voice using Generative Adversarial Networks

2019-12-01 · NeurIPS 2019 12 · Yandong Wen, Bhiksha Raj, Rita Singh

Voice profiling aims at inferring various human parameters from their speech, e.g. gender, age, etc. In this paper, we address the challenge posed by a subtask of voice profiling - reconstructing someone's face from their voice. The task is designed to answer the question: given an audio clip spoken by an unseen person, can we picture a face that has as many common elements, or associations as possible with the speaker, in terms of identity? To address this problem, we propose a simple but effective computational framework based on generative adversarial networks (GANs). The network learns to generate faces from voices by matching the identities of generated faces to those of the speakers, on a training set. We evaluate the performance of the network by leveraging a closely related task - cross-modal matching. The results show that our model is able to generate faces that match several biometric characteristics of the speaker, and results in matching accuracies that are much better than chance. The code is publicly available in https://github.com/cmu-mlsp/reconstructing_faces_from_voices

📄 PDF Abstract BibTeX

Code (1)

cmu-mlsp/reconstructing_faces_from_voices 공식 구현 pytorch

Tasks

Face Reconstruction

Similar Papers 제목 키워드 기반

Voice Aging with Audio-Visual Style Transfer

2021-10-05 · Justin Wilson, Sunyeong Park, Seunghye J. Wilson, Ming C. Lin

Face aging techniques have used generative adversarial networks (GANs) and style transfer learning to transform one's appearance to look younger/older. Identity is maintained by conditioning these generative networks on …

Style TransferTransfer Learning

SingGAN: Generative Adversarial Network For High-Fidelity Singing Voice Generation

2021-10-14 · Rongjie Huang, Chenye Cui, Feiyang Chen, Yi Ren 외

Deep generative models have achieved significant progress in speech synthesis to date, while high-fidelity singing voice synthesis is still an open problem for its long continuous pronunciation, rich high-frequency parts…

Generative Adversarial NetworkGPUSinging Voice SynthesisSpeech Synthesis+3

Reconstructing faces from voices

2019-05-25 · Yandong Wen, Rita Singh, Bhiksha Raj

Voice profiling aims at inferring various human parameters from their speech, e.g. gender, age, etc. In this paper, we address the challenge posed by a subtask of voice profiling - reconstructing someone's face from thei…

Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GAN

2022-09-21 · Yin-Ping Cho, Yu Tsao, Hsin-Min Wang, Yi-Wen Liu

Singing voice synthesis (SVS) is the computer production of a human-like singing voice from given musical scores. To accomplish end-to-end SVS effectively and efficiently, this work adopts the acoustic model-neural vocod…

DenoisingGenerative Adversarial NetworkSinging Voice Synthesis

Robust One-Shot Singing Voice Conversion

2022-10-20 · Naoya Takahashi, Mayank Kumar Singh, Yuki Mitsufuji

Recent progress in deep generative models has improved the quality of voice conversion in the speech domain. However, high-quality singing voice conversion (SVC) of unseen singers remains challenging due to the wider var…

Voice Conversion