paper-with-me

홈 › Papers

Differentiable Time-Varying Linear Prediction in the Context of End-to-End Analysis-by-Synthesis

2024-06-07 · Chin-Yun Yu, György Fazekas

Training the linear prediction (LP) operator end-to-end for audio synthesis in modern deep learning frameworks is slow due to its recursive formulation. In addition, frame-wise approximation as an acceleration method cannot generalise well to test time conditions where the LP is computed sample-wise. Efficient differentiable sample-wise LP for end-to-end training is the key to removing this barrier. We generalise the efficient time-invariant LP implementation from the GOLF vocoder to time-varying cases. Combining this with the classic source-filter model, we show that the improved GOLF learns LP coefficients and reconstructs the voice better than its frame-wise counterparts. Moreover, in our listening test, synthesised outputs from GOLF scored higher in quality ratings than the state-of-the-art differentiable WORLD vocoder.

📄 PDF Abstract BibTeX arXiv:2406.05128

Code (4)

yoyololicon/golf 공식 구현 pytorch
yoyololicon/torchlpc 공식 구현 pytorch
diffapf/torchlpc pytorch
iamycy/golf pytorch

Tasks

Audio Synthesis

Similar Papers 제목 키워드 기반

Differentiable Grey-box Modelling of Phaser Effects using Frame-based Spectral Processing

2023-06-02 · Alistair Carson, Cassia Valentini-Botinhao, Simon King, Stefan Bilbao

Machine learning approaches to modelling analog audio effects have seen intensive investigation in recent years, particularly in the context of non-linear time-invariant effects such as guitar amplifiers. For modulation …

Probabilistic sequential matrix factorization

2019-10-09 · Ömer Deniz Akyildiz, Gerrit J. J. van den Burg, Theodoros Damoulas, Mark F. J. Steel

We introduce the probabilistic sequential matrix factorization (PSMF) method for factorizing time-varying and non-stationary datasets consisting of high-dimensional time-series. In particular, we consider nonlinear Gauss…

ImputationMultivariate Time Series ForecastingMultivariate Time Series ImputationState Space Models+3

Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking

2021-02-19 · Paula Gradu, John Hallman, Daniel Suo, Alex Yu 외

We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite. The introduced environments allow auto-differentiat…

BenchmarkingOpenAI Gym

Online Proximal-ADMM For Time-varying Constrained Convex Optimization

2020-10-10

This paper considers a convex optimization problem with cost and constraints that evolve over time. The function to be minimized is strongly convex and possibly non-differentiable, and variables are coupled through linea…

Learning Constrained Adaptive Differentiable Predictive Control Policies With Guarantees

2020-04-23 · Jan Drgona, Aaron Tuor, Draguna Vrabie

We present differentiable predictive control (DPC), a method for learning constrained neural control policies for linear systems with probabilistic performance guarantees. We employ automatic differentiation to obtain di…

Continuous ControlImitation LearningModel Predictive Control