Files in this item

FilesDescriptionFormat

application/pdf

application/pdfZHAO-THESIS-2020.pdf (5MB)
(no description provided)PDF

Description

Title:Differential DSP: An audio toolbox for end-to-end ml
Author(s):Zhao, An
Advisor(s):Smaragdis, Paris
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):Differential
DSP
DDSP
Machine learning
Audio
Classification
Abstract:The short-time Fourier transform (STFT) has been a staple of signal processing, often being the first step for many audio tasks. A very familiar process when using the STFT is the search for the best STFT parameters, as they often have significant side effects if chosen poorly. These parameters are often de ned in terms of an integer number of samples, which makes their optimization non-trivial. We present a toolbox that allows us to obtain gradients for commonly used audio filter parameters, and for STFT parameters with respect to arbitrary cost functions, thus enabling gradient descent optimization of quantities like the STFT window length or the STFT hop size. We do so for parameter values that stay constant throughout an input, but also for cases where these parameters have to dynamically change over time to accommodate varying signal characteristics.
Issue Date:2020-12-10
Type:Thesis
URI:http://hdl.handle.net/2142/109453
Rights Information:Copyright 2020 An Zhao
Date Available in IDEALS:2021-03-05
Date Deposited:2020-12


This item appears in the following Collection(s)

Item Statistics