Publication Details
BUT ASR System for BABEL Surprise Evaluation 2014
Veselý Karel, Ing., Ph.D. (DCGM)
Szőke Igor, Ing., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Grézl František, Ing., Ph.D. (DCGM)
Hannemann Mirko, Ph.D.
Černocký Jan, prof. Dr. Ing. (DCGM)
speech recognition, discriminative training, bottle-neck neural networks, deep neural networks, adaptation of neural networks, noisy speech
This paper describes Brno University of Technology (BUT) ASR system for 2014 BABEL Surprise language evaluation (Tamil).
The paper describes Brno University of Technology (BUT) ASR system for 2014 BABEL Surprise language evaluation (Tamil). While being largely based on our previous work, two original contributions were brought: (1) speaker-adapted bottle-neck neural network (BN) features were investigated as an input to DNN recognizer and semi-supervised training was found effective. (2) Adding of noise to training data outperformed a classical de-noising technique while dealing with noisy test data was found beneficial, and the performance of this approach was verified on a relatively clean training/test data setup from a different language. All results are reported on BABEL 2014 Tamil data.
@inproceedings{BUT111503,
author="Martin {Karafiát} and Karel {Veselý} and Igor {Szőke} and Lukáš {Burget} and František {Grézl} and Mirko {Hannemann} and Jan {Černocký}",
title="BUT ASR System for BABEL Surprise Evaluation 2014",
booktitle="Proceedings of 2014 Spoken Language Technology Workshop",
year="2014",
pages="501--506",
publisher="IEEE Signal Processing Society",
address="South Lake Tahoe, Nevada",
doi="10.1109/SLT.2014.7078625",
isbn="978-1-4799-7129-9",
url="https://www.fit.vut.cz/research/publication/10799/"
}