Sounderfeit: Cloning a Physical Model with Conditional Adversarial Autoencoders
An adversarial autoencoder conditioned on known parameters of a physical modeling bowed string synthesizer is evaluated for use in parameter estimation and resynthesis tasks. Latent dimensions are provided to capture variance not explained by the conditional parameters. Results are compared with and without the adversarial training, and a system capable of "copying" a given parameter-signal bidirectional relationship is examined. A real-time synthesis system built on a generative, conditioned and regularized neural network is presented, allowing to construct engaging sound synthesizers based purely on recorded data.
Code (0)
등록된 구현이 없습니다.
Tasks
parameter estimationResynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sounderfeit: Cloning a Physical Model using a Conditional Adversarial Autoencoder
An adversarial autoencoder conditioned on known parameters of a physical modeling bowed string synthesizer is evaluated for use in parameter estimation and resynthesis tasks. Latent dimensions are provided to capture var…
parameter estimationResynthesisTheoretical Insights into the Use of Structural Similarity Index In Generative Models and Inferential Autoencoders
Generative models and inferential autoencoders mostly make use of $\ell_2$ norm in their optimization objectives. In order to generate perceptually better images, this short paper theoretically discusses how to use Struc…
Dimensionality ReductionImage GenerationImage Quality AssessmentSSIMABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning
Given a dataset of expert agent interactions with an environment of interest, a viable method to extract an effective agent policy is to estimate the maximum likelihood policy indicated by this data. This approach is com…
Generative Adversarial NetworkImitation LearningPhysical Adversarial Attacks Against End-to-End Autoencoder Communication Systems
We show that end-to-end learning of communication systems through deep neural network (DNN) autoencoders can be extremely vulnerable to physical adversarial attacks. Specifically, we elaborate how an attacker can craft e…
Multi-modal Adversarial Training for Zero-Shot Voice Cloning
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 nat…
Decodertext-to-speechText to SpeechVoice Cloning