Článek ve sborníku konference

KOMBRINK Stefan, MIKOLOV Tomáš, KARAFIÁT Martin a BURGET Lukáš. Recurrent Neural Network based Language Modeling in Meeting Recognition. In: Proceedings of Interspeech 2011. Florence: International Speech Communication Association, 2011, s. 2877-2880. ISBN 978-1-61839-270-1. ISSN 1990-9772.
Jazyk publikace:angličtina
Název publikace:Recurrent Neural Network based Language Modeling in Meeting Recognition
Název (cs):Jazykový model založený na rekurentních neuronových sítích pro rozpoznávání řeči z meetingů
Strany:2877-2880
Sborník:Proceedings of Interspeech 2011
Konference:Interspeech 2011
Místo vydání:Florence, IT
Rok:2011
ISBN:978-1-61839-270-1
Časopis:Proceedings of Interspeech, roč. 2011, č. 8, FR
ISSN:1990-9772
Vydavatel:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/kombrink_interspeech2011_792.pdf [PDF]
Klíčová slova
automatic speech recognition, language modeling, recurrent neural networks, rescoring, adaptation
Anotace
Tento článek pojednává o jazykovém modelu založeném na rekurentních neuronových sítích pro rozpoznávání řeči z meetingů.
Abstrakt
We use recurrent neural network (RNN) based language models to improve the BUT English meeting recognizer. On the baseline setup using the original language models we decrease word error rate (WER) more than 1% absolute by n-best list rescoring and language model adaptation. When n-gram language models are trained on the same moderately sized data set as the RNN models, improvements are higher yielding a system which performs comparable to the baseline. A noticeable improvement was observed with unsupervised adaptation of RNN models. Furthermore, we examine the influence of word history on WER and show how to speed-up rescoring by caching common prefix strings.
BibTeX:
@INPROCEEDINGS{
   author = {Stefan Kombrink and Tom{\'{a}}{\v{s}} Mikolov and
	Martin Karafi{\'{a}}t and Luk{\'{a}}{\v{s}} Burget},
   title = {Recurrent Neural Network based Language Modeling
	in Meeting Recognition},
   pages = {2877--2880},
   booktitle = {Proceedings of Interspeech 2011},
   journal = {Proceedings of Interspeech},
   volume = 2011,
 number = 8,
   year = 2011,
   location = {Florence, IT},
   publisher = {International Speech Communication Association},
   ISBN = {978-1-61839-270-1},
   ISSN = {1990-9772},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.cs?id=9760}
}

Vaše IPv4 adresa: 3.226.251.81
Přepnout na https