@inproceedings{michel-etal-2016-rwth,
title = "The {RWTH} {A}achen {LVCSR} system for {IWSLT}-2016 {G}erman Skype conversation recognition task",
author = {Michel, Wilfried and
T{\"u}ske, Zolt{\'a}n and
Shaik, M. Ali Basha and
Schl{\"u}ter, Ralf and
Ney, Hermann},
editor = {Cettolo, Mauro and
Niehues, Jan and
St{\"u}ker, Sebastian and
Bentivogli, Luisa and
Cattoni, Rolando and
Federico, Marcello},
booktitle = "Proceedings of the 13th International Conference on Spoken Language Translation",
month = dec # " 8-9",
year = "2016",
address = "Seattle, Washington D.C",
publisher = "International Workshop on Spoken Language Translation",
url = "https://aclanthology.org/2016.iwslt-1.17",
abstract = "In this paper the RWTH large vocabulary continuous speech recognition (LVCSR) systems developed for the IWSLT-2016 evaluation campaign are described. This evaluation campaign focuses on transcribing spontaneous speech from Skype recordings. State-of-the-art bidirectional long short-term memory (LSTM) and deep, multilingually boosted feed-forward neural network (FFNN) acoustic models are trained an narrow and broadband features. An open vocabulary approach using subword units is also considered. LSTM and count-based full word and hybrid backoff language modeling methods are used to model the morphological richness of the German language. All these approaches are combined using confusion network combination (CNC) to yield a competitive WER.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="michel-etal-2016-rwth">
<titleInfo>
<title>The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilfried</namePart>
<namePart type="family">Michel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoltán</namePart>
<namePart type="family">Tüske</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="given">Ali</namePart>
<namePart type="given">Basha</namePart>
<namePart type="family">Shaik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralf</namePart>
<namePart type="family">Schlüter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hermann</namePart>
<namePart type="family">Ney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-dec 8-9</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Conference on Spoken Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mauro</namePart>
<namePart type="family">Cettolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolando</namePart>
<namePart type="family">Cattoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Workshop on Spoken Language Translation</publisher>
<place>
<placeTerm type="text">Seattle, Washington D.C</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper the RWTH large vocabulary continuous speech recognition (LVCSR) systems developed for the IWSLT-2016 evaluation campaign are described. This evaluation campaign focuses on transcribing spontaneous speech from Skype recordings. State-of-the-art bidirectional long short-term memory (LSTM) and deep, multilingually boosted feed-forward neural network (FFNN) acoustic models are trained an narrow and broadband features. An open vocabulary approach using subword units is also considered. LSTM and count-based full word and hybrid backoff language modeling methods are used to model the morphological richness of the German language. All these approaches are combined using confusion network combination (CNC) to yield a competitive WER.</abstract>
<identifier type="citekey">michel-etal-2016-rwth</identifier>
<location>
<url>https://aclanthology.org/2016.iwslt-1.17</url>
</location>
<part>
<date>2016-dec 8-9</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task
%A Michel, Wilfried
%A Tüske, Zoltán
%A Shaik, M. Ali Basha
%A Schlüter, Ralf
%A Ney, Hermann
%Y Cettolo, Mauro
%Y Niehues, Jan
%Y Stüker, Sebastian
%Y Bentivogli, Luisa
%Y Cattoni, Rolando
%Y Federico, Marcello
%S Proceedings of the 13th International Conference on Spoken Language Translation
%D 2016
%8 dec 8 9
%I International Workshop on Spoken Language Translation
%C Seattle, Washington D.C
%F michel-etal-2016-rwth
%X In this paper the RWTH large vocabulary continuous speech recognition (LVCSR) systems developed for the IWSLT-2016 evaluation campaign are described. This evaluation campaign focuses on transcribing spontaneous speech from Skype recordings. State-of-the-art bidirectional long short-term memory (LSTM) and deep, multilingually boosted feed-forward neural network (FFNN) acoustic models are trained an narrow and broadband features. An open vocabulary approach using subword units is also considered. LSTM and count-based full word and hybrid backoff language modeling methods are used to model the morphological richness of the German language. All these approaches are combined using confusion network combination (CNC) to yield a competitive WER.
%U https://aclanthology.org/2016.iwslt-1.17
Markdown (Informal)
[The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task](https://aclanthology.org/2016.iwslt-1.17) (Michel et al., IWSLT 2016)
ACL