Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Acoustic Matching by Embedding Impulse Responses

Abstract: 

The goal of acoustic matching is to transform an audio recording made in one acoustic environment to sound as if it had been recorded in a different environment, based on reference audio from the target environment. This paper introduces a deep learning solution for two parts of the acoustic matching problem. First, we characterize acoustic environments by mapping audio into a low-dimensional embedding invariant to speech content and speaker identity. Next, a waveform-to-waveform neural network conditioned on this embedding learns to transform an input waveform to match the acoustic qualities encoded in the target embedding. Listening tests on both simulated and real environments show that the proposed approach improves on state-of-the-art baseline methods.

up
0 users have voted:

Paper Details

Authors:
Adam Finkelstein
Submitted On:
23 May 2020 - 11:34am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Jiaqi Su
Paper Code:
5239
Document Year:
2020
Cite

Document Files

presentation

(9)

Subscribe

[1] Adam Finkelstein, "Acoustic Matching by Embedding Impulse Responses", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5433. Accessed: Jun. 06, 2020.
@article{5433-20,
url = {http://sigport.org/5433},
author = {Adam Finkelstein },
publisher = {IEEE SigPort},
title = {Acoustic Matching by Embedding Impulse Responses},
year = {2020} }
TY - EJOUR
T1 - Acoustic Matching by Embedding Impulse Responses
AU - Adam Finkelstein
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5433
ER -
Adam Finkelstein. (2020). Acoustic Matching by Embedding Impulse Responses. IEEE SigPort. http://sigport.org/5433
Adam Finkelstein, 2020. Acoustic Matching by Embedding Impulse Responses. Available at: http://sigport.org/5433.
Adam Finkelstein. (2020). "Acoustic Matching by Embedding Impulse Responses." Web.
1. Adam Finkelstein. Acoustic Matching by Embedding Impulse Responses [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5433