Publication Details

Robust Speech Recognition in Unknown Reverberant and Noisy Conditions

HSIAO, R.; MA, J.; HARTMANN, W.; KARAFIÁT, M.; GRÉZL, F.; BURGET, L.; SZŐKE, I.; ČERNOCKÝ, J.; WATANABE, S.; CHEN, Z.; MALLIDI, S.; HEŘMANSKÝ, H.; TSAKALIDIS, S.; SCHWARTZ, R. Robust Speech Recognition in Unknown Reverberant and Noisy Conditions. In Proceedings of 2015 IEEE Automatic Speech Recognition and Understanding Workshop. Scottsdale, Arizona: IEEE Signal Processing Society, 2015. p. 533-538. ISBN: 978-1-4799-7291-3.
Czech title
Robustní rozpoznávání řeči v neznámých podmínkách s reverberací a šumem
Type
conference paper
Language
English
Authors
Hsiao Roger (FIT)
Ma Jeff
Hartmann William (FIT)
Karafiát Martin, Ing., Ph.D. (DCGM)
Grézl František, Ing., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Szőke Igor, Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
Watanabe Shinji (FIT)
Chen Zhuo (FIT)
Mallidi Sri Harish (FIT)
Heřmanský Hynek, prof. Ing. (DCGM)
Tsakalidis Stavros (FIT)
Schwartz Richard (FIT)
URL
Keywords

ASpIRE challenge, robust speech recognition

Abstract

In this paper, we describe our work on the ASpIRE (Automatic Speech recognition In Reverberant Environments) challenge, which aims to assess the robustness of automatic speech recognition (ASR) systems. The main characteristic of the challenge is developing a high-performance system without access to matched training and development data. While the evaluation data are recorded with far-field microphones in noisy and reverberant rooms, the training data are telephone speech and close talking. Our approach to this challenge includes speech enhancement, neural network methods and acoustic model adaptation, We show that these techniques can successfully alleviate the performance degradation due to noisy audio and data mismatch.

Annotation

In this paper, we describe our work in the ASpIRE challenge. We experiment and evaluate different approaches to tackling the performance degradation due to noise and data mismatch. Our approaches include audio enhancement, data augmentation, unsupervised DNN adaptation, and system combination.

Published
2015
Pages
533–538
Proceedings
Proceedings of 2015 IEEE Automatic Speech Recognition and Understanding Workshop
ISBN
978-1-4799-7291-3
Publisher
IEEE Signal Processing Society
Place
Scottsdale, Arizona
DOI
10.1109/ASRU.2015.7404841
UT WoS
000380604800076
EID Scopus
2-s2.0-84964470918
BibTeX 
@inproceedings{BUT120392,
  author="Roger {Hsiao} and Jeff {Ma} and William {Hartmann} and Martin {Karafiát} and František {Grézl} and Lukáš {Burget} and Igor {Szőke} and Jan {Černocký} and Shinji {Watanabe} and Zhuo {Chen} and Sri Harish {Mallidi} and Hynek {Heřmanský} and Stavros {Tsakalidis} and Richard {Schwartz}",
  title="Robust Speech Recognition in Unknown Reverberant and Noisy Conditions",
  booktitle="Proceedings of 2015 IEEE Automatic Speech Recognition and Understanding Workshop",
  year="2015",
  pages="533--538",
  publisher="IEEE Signal Processing Society",
  address="Scottsdale, Arizona",
  doi="10.1109/ASRU.2015.7404841",
  isbn="978-1-4799-7291-3",
  url="https://www.fit.vut.cz/research/publication/11067/"
}
Back to top