Conference paper

KOMBRINK Stefan. OOV detection in LVCSR using neural networks. In: Proc. STUDENT EEICT 2008. Brno: Faculty of Electrical Engineering and Communication BUT, 2008, p. 3. ISBN 978-80-214-3617-6.
Publication language:english
Original title:OOV detection in LVCSR using neural networks
Title (cs):OOV detekce v LVCSR pomocí neuronových sítí
Pages:3
Proceedings:Proc. STUDENT EEICT 2008
Conference:Student EEICT 2008
Place:Brno, CZ
Year:2008
ISBN:978-80-214-3617-6
Publisher:Faculty of Electrical Engineering and Communication BUT
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2008/kombrink_eeict.pdf [PDF]
Keywords
speech recognition
Annotation
The work is on OOV detection in LVCSR using neural networks
Abstract
Confidence measures and classifying techniques are widely used for the recognition error detection task in LVCSR (Large Vocabulary Continuous Speech Recognition). But in many recognition scenarios the amount of words not included in the dictionary (e.g. real names, neologisms) lead to so-called OOV (Out Of Vocabulary) errors which increase the WER (Word Error Rate) even more. The hereby described work acknowledges and investigates further improvements of an OOV detection task performed by combining strong and weak phone posterior features using neural networks based on [ICASSP08] and the use of phone context.
BibTeX:
@INPROCEEDINGS{
   author = {Stefan Kombrink},
   title = {OOV detection in LVCSR using neural networks},
   pages = {3},
   booktitle = {Proc. STUDENT EEICT 2008},
   year = {2008},
   location = {Brno, CZ},
   publisher = {Faculty of Electrical Engineering and Communication BUT},
   ISBN = {978-80-214-3617-6},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9097}
}

Your IPv4 address: 54.225.26.154
Switch to IPv6 connection

DNSSEC [dnssec]