Publication Details
Speech Enhancement Using End-to-End Speech Recognition Objectives
WANG, X.
Baskar Murali Karthick, Ing., Ph.D.
Watanabe Shinji
TANIGUCHI, T.
TRAN, D.
FUJITA, Y.
speech enhancement, speech recognition, neural dereverberation, neural
beamformer, training objectives
Speech enhancement systems, which denoise and dereverberate distorted signals,
are usually optimized based on signal reconstruction objectives including the
maximum likelihood and minimum mean square error. However, emergent end-to-end
neural methods enable to optimize the speech enhancement system with more
applicationoriented objectives. For example, we can jointly optimize speech
enhancement and automatic speech recognition (ASR) only with ASR error
minimization criteria. The major contribution of this paper is to investigate how
a system optimized based on the ASR objective improves the speech enhancement
quality on various signal level metrics in addition to the ASR word error rate
(WER) metric. We use a recently developed multichannel end-to-end (ME2E) system,
which integrates neural dereverberation, beamforming, and attention-based speech
recognition within a single neural network. Additionally, we propose to extend
the dereverberation sub network of ME2E by dynamically varying the filter order
in linear prediction by using reinforcement learning, and extend the beamforming
subnetwork by incorporating the estimation of a speech distortion factor. The
experiments reveal how well different signal level metrics correlate with the WER
metric, and verify that learning-based speech enhancement can be realized by
end-to-end ASR training objectives without using parallel clean and noisy data.
@inproceedings{BUT170323,
author="SUBRAMANIAN, A. and WANG, X. and BASKAR, M. and WATANABE, S. and TANIGUCHI, T. and TRAN, D. and FUJITA, Y.",
title="Speech Enhancement Using End-to-End Speech Recognition Objectives",
booktitle="IEEE Workshop on Applications of Signal Processing to Audio and Acoustics",
year="2019",
pages="234--238",
publisher="IEEE Signal Processing Society",
address="New Paltz, NY",
doi="10.1109/WASPAA.2019.8937250",
isbn="978-1-7281-1123-0",
url="https://ieeexplore.ieee.org/document/8937250"
}