Článek ve sborníku konference

ŽMOLÍKOVÁ Kateřina, KARAFIÁT Martin, VESELÝ Karel, DELCROIX Marc, WATANABE Shinji, BURGET Lukáš a ČERNOCKÝ Jan. Data selection by sequence summarizing neural network in mismatch condition training. In: Proceedings of Interspeech 2016. San Francisco: International Speech Communication Association, 2016, s. 2354-2358. ISBN 978-1-5108-3313-5. Dostupné z: https://www.semanticscholar.org/paper/Data-Selection-by-Sequence-Summarizing-Neural-Zmol%C3%ADkov%C3%A1-Karafi%C3%A1t/bc1832e8b8d4e5edf987e1562b578bd9aa5e18a9
Jazyk publikace:angličtina
Název publikace:Data selection by sequence summarizing neural network in mismatch condition training
Název (cs):Výběr dat pomocí sekvenční sumarizační neuronové sítě v trénování na datech z odlišných podmínek
Strany:2354-2358
Sborník:Proceedings of Interspeech 2016
Konference:Interspeech 2016
Místo vydání:San Francisco, US
Rok:2016
URL:https://www.semanticscholar.org/paper/Data-Selection-by-Sequence-Summarizing-Neural-Zmol%C3%ADkov%C3%A1-Karafi%C3%A1t/bc1832e8b8d4e5edf987e1562b578bd9aa5e18a9
ISBN:978-1-5108-3313-5
DOI:10.21437/Interspeech.2016-741
Vydavatel:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2016/zmolikova_interpeech2016_IS160741.pdf [PDF]
Klíčová slova
Automatic speech recognition, Data augmentation, Data selection, Mismatch training condition, Sequence summarization
Anotace
Článek pojednává o výběru dat pomocí sekvenční sumarizační neuronové sítě v trénování na datech z odlišných podmínek.
Abstrakt
Data augmentation is a simple and efficient technique to improve the robustness of a speech recognizer when deployed in mismatched training-test conditions. Our paper proposes a new approach for selecting data with respect to similarity of acoustic conditions. The similarity is computed based on a sequence summarizing neural network which extracts vectors containing acoustic summary (e.g. noise and reverberation characteristics) of an utterance. Several configurations of this network and different methods of selecting data using these "summary-vectors" were explored. The results are reported on a mismatched condition using AMI training set with the proposed data selection and CHiME3 test set.
BibTeX:
@INPROCEEDINGS{
   author = {Kate{\v{r}}ina {\v{Z}}mol{\'{i}}kov{\'{a}} and
	Martin Karafi{\'{a}}t and Karel Vesel{\'{y}} and
	Marc Delcroix and Shinji Watanabe and
	Luk{\'{a}}{\v{s}} Burget and Jan
	{\v{C}}ernock{\'{y}}},
   title = {Data selection by sequence summarizing neural
	network in mismatch condition training},
   pages = {2354--2358},
   booktitle = {Proceedings of Interspeech 2016},
   year = 2016,
   location = {San Francisco, US},
   publisher = {International Speech Communication Association},
   ISBN = {978-1-5108-3313-5},
   doi = {10.21437/Interspeech.2016-741},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.cs?id=11271}
}

Vaše IPv4 adresa: 3.81.28.94
Přepnout na https