Kapitola v knize

KARAFIÁT Martin, VESELÝ Karel, ŽMOLÍKOVÁ Kateřina, DELCROIX Marc, WATANABE Shinji, BURGET Lukáš, ČERNOCKÝ Jan a SZŐKE Igor. Training Data Augmentation and Data Selection. New Era for Robust Speech Recognition: Exploiting Deep Learning. Heidelberg: Springer International Publishing, 2017, s. 245-260. ISBN 978-3-319-64679-4. Dostupné z: http://www.springer.com/gp/book/9783319646794#aboutBook
Jazyk publikace:angličtina
Název publikace:Training Data Augmentation and Data Selection
Název (cs):Množení a selekce trénovacích dat
Strany:245-260
Kniha:New Era for Robust Speech Recognition: Exploiting Deep Learning
Řada knih:Computer Science, Artificial Intelligence
Místo vydání:Heidelberg, DE
Rok:2017
URL:http://www.springer.com/gp/book/9783319646794#aboutBook
ISBN:978-3-319-64679-4
DOI:10.1007/978-3-319-64680-0_10
Vydavatel:Springer International Publishing
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2017/karafiat_book%20chapter_Springer_2017.pdf [PDF]
Klíčová slova
training data, augmentation, data selection
Anotace
Kapitola 10 knihy: Nová éra robustního rozpoznávání řeči: využití hlubokého učení, pojednává o množení a selekci trénovacích dat.
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 work, conducted during the JSALT 2015 workshop, aimed at the development of: (1) Data augmentation strategies including noising and reverberation. They were tested in combination with two approaches to signal enhancement: a carefully engineered WPE dereverberation and a learned DNN-based denoising autoencoder. (2) Proposing a novel technique for extracting an informative vector from a Sequence Summarizing Neural Network (SSNN). Similarly to i-vector extractor, the SSNN produces a "summary vector", representing an acoustic summary of an utterance. Such vector can be used directly for adaptation, but the main usage matching the aim of this chapter is for selection of augmented training data. All techniques were tested on the AMI training set and CHiME3 test set.
BibTeX:
@INBOOK{
   author = {Martin Karafi{\'{a}}t and Karel Vesel{\'{y}} and
	Kate{\v{r}}ina {\v{Z}}mol{\'{i}}kov{\'{a}} and Marc Delcroix
	and Shinji Watanabe and Luk{\'{a}}{\v{s}} Burget and Jan
	{\v{C}}ernock{\'{y}} and Igor Sz{\H{o}}ke},
   title = {Training Data Augmentation and Data Selection},
   pages = {245--260},
   booktitle = {New Era for Robust Speech Recognition: Exploiting Deep
	Learning},
   series = {Computer Science, Artificial Intelligence},
   year = {2017},
   location = {Heidelberg, DE},
   publisher = {Springer International Publishing},
   ISBN = {978-3-319-64679-4},
   doi = {10.1007/978-3-319-64680-0_10},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.cs?id=11588}
}

Vaše IPv4 adresa: 54.198.104.202
Přepnout na IPv6 spojení

DNSSEC [dnssec]