Publication Details
Building and Evaluation of a Real Room Impulse Response Dataset
Skácel Miroslav, Ing.
Mošner Ladislav, Ing. (DCGM)
Paliesek Jakub, Ing.
Černocký Jan, prof. Dr. Ing. (DCGM)
far-field, automatic speech recognition, room impulse response, reverberation,
SineSweep, Maximum Length Sequence, noise, deep neural network, Kaldi, AMI
This paper presents BUT ReverbDB - a dataset of real room impulse responses
(RIR), background noises and re-transmitted speech data. The retransmitted data
includes LibriSpeech test-clean, 2000 HUB5 English evaluation and part of 2010
NIST Speaker Recognition Evaluation datasets. We provide a detailed description
of RIR collection (hardware, software, post-processing) that can serve as
a "cook-book" for similar efforts. We also validate BUT ReverbDB in two sets of
automatic speech recognition (ASR) experiments and draw conclusions for
augmenting ASR training data with real and artificially generated RIRs. We show
that a limited number of real RIRs, carefully selected to match the target
environment, provide results comparable to a large number of artificially
generated RIRs, and that both sets can be combined to achieve the best ASR
results. The dataset is distributed for free under a non-restrictive license and
it currently contains data from 8 rooms, which is growing. The distribution
package also contains a Kaldi-based recipe for augmenting publicly available AMI
close-talk meeting data and test the results on an AMI single distant microphone
set, allowing it to reproduce our experiments.
@article{BUT159973,
author="Igor {Szőke} and Miroslav {Skácel} and Ladislav {Mošner} and Jakub {Paliesek} and Jan {Černocký}",
title="Building and Evaluation of a Real Room Impulse Response Dataset",
journal="IEEE J-STSP",
year="2019",
volume="13",
number="4",
pages="863--876",
doi="10.1109/JSTSP.2019.2917582",
issn="1932-4553",
url="https://ieeexplore.ieee.org/document/8717722"
}