Detail výsledku
Robust Speech Recognition in Unknown Reverberant and Noisy Conditions
Ma Jeff
Hartmann William
Karafiát Martin, Ing., Ph.D., UPGM (FIT)
Grézl František, Ing., Ph.D., UPGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., UPGM (FIT)
Szőke Igor, Ing., Ph.D., UPGM (FIT)
Černocký Jan, prof. Dr. Ing., UPGM (FIT)
Watanabe Shinji
Chen Zhuo
Mallidi Sri Harish, FIT (FIT)
Heřmanský Hynek, prof. Ing., Dr. Eng., UPGM (FIT)
Tsakalidis Stavros, FIT (FIT)
Schwartz Richard, FIT (FIT)
In this paper, we describe our work on the ASpIRE (AutomaticSpeech recognition In Reverberant Environments)challenge, which aims to assess the robustness of automaticspeech recognition (ASR) systems. The main characteristic ofthe challenge is developing a high-performance system withoutaccess to matched training and development data. Whilethe evaluation data are recorded with far-field microphones innoisy and reverberant rooms, the training data are telephonespeech and close talking. Our approach to this challengeincludes speech enhancement, neural network methods andacoustic model adaptation, We show that these techniquescan successfully alleviate the performance degradation due tonoisy audio and data mismatch.
ASpIRE challenge, robust speech recognition
@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/"
}
Dolování infoRmAcí z řeči Pořízené vzdÁlenými miKrofony, MV, Bezpečnostní výzkum České republiky 2015-2020, VI20152020025, zahájení: 2015-10-01, ukončení: 2020-09-30, ukončen
IARPA Tvorba rozpoznávačů řeči pro vyhledávání klíčových slov v novém jazyce s omezenými trénovacími daty za týden (BABEL) - Babelon, BBN, zahájení: 2012-03-05, ukončení: 2016-11-04, ukončen