@inproceedings{scherbakov-etal-2021-anlirika,
title = "Anlirika: An {LSTM}{--}{CNN} Flow Twister for Spoken Language Identification",
author = "Scherbakov, Andreas and
Whittle, Liam and
Kumar, Ritesh and
Singh, Siddharth and
Coleman, Matthew and
Vylomova, Ekaterina",
editor = {Vylomova, Ekaterina and
Salesky, Elizabeth and
Mielke, Sabrina and
Lapesa, Gabriella and
Kumar, Ritesh and
Hammarstr{\"o}m, Harald and
Vuli{\'c}, Ivan and
Korhonen, Anna and
Reichart, Roi and
Ponti, Edoardo Maria and
Cotterell, Ryan},
booktitle = "Proceedings of the Third Workshop on Computational Typology and Multilingual NLP",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigtyp-1.14",
doi = "10.18653/v1/2021.sigtyp-1.14",
pages = "145--148",
abstract = "The paper presents Anlirika{'}s submission to SIGTYP 2021 Shared Task on Robust Spoken Language Identification. The task aims at building a robust system that generalizes well across different domains and speakers. The training data is limited to a single domain only with predominantly single speaker per language while the validation and test data samples are derived from diverse dataset and multiple speakers. We experiment with a neural system comprising a combination of dense, convolutional, and recurrent layers that are designed to perform better generalization and obtain speaker-invariant representations. We demonstrate that the task in its constrained form (without making use of external data or augmentation the train set with samples from the validation set) is still challenging. Our best system trained on the data augmented with validation samples achieves 29.9{\%} accuracy on the test data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scherbakov-etal-2021-anlirika">
<titleInfo>
<title>Anlirika: An LSTM–CNN Flow Twister for Spoken Language Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Scherbakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liam</namePart>
<namePart type="family">Whittle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Coleman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Computational Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">Mielke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harald</namePart>
<namePart type="family">Hammarström</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper presents Anlirika’s submission to SIGTYP 2021 Shared Task on Robust Spoken Language Identification. The task aims at building a robust system that generalizes well across different domains and speakers. The training data is limited to a single domain only with predominantly single speaker per language while the validation and test data samples are derived from diverse dataset and multiple speakers. We experiment with a neural system comprising a combination of dense, convolutional, and recurrent layers that are designed to perform better generalization and obtain speaker-invariant representations. We demonstrate that the task in its constrained form (without making use of external data or augmentation the train set with samples from the validation set) is still challenging. Our best system trained on the data augmented with validation samples achieves 29.9% accuracy on the test data.</abstract>
<identifier type="citekey">scherbakov-etal-2021-anlirika</identifier>
<identifier type="doi">10.18653/v1/2021.sigtyp-1.14</identifier>
<location>
<url>https://aclanthology.org/2021.sigtyp-1.14</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>145</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Anlirika: An LSTM–CNN Flow Twister for Spoken Language Identification
%A Scherbakov, Andreas
%A Whittle, Liam
%A Kumar, Ritesh
%A Singh, Siddharth
%A Coleman, Matthew
%A Vylomova, Ekaterina
%Y Vylomova, Ekaterina
%Y Salesky, Elizabeth
%Y Mielke, Sabrina
%Y Lapesa, Gabriella
%Y Kumar, Ritesh
%Y Hammarström, Harald
%Y Vulić, Ivan
%Y Korhonen, Anna
%Y Reichart, Roi
%Y Ponti, Edoardo Maria
%Y Cotterell, Ryan
%S Proceedings of the Third Workshop on Computational Typology and Multilingual NLP
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F scherbakov-etal-2021-anlirika
%X The paper presents Anlirika’s submission to SIGTYP 2021 Shared Task on Robust Spoken Language Identification. The task aims at building a robust system that generalizes well across different domains and speakers. The training data is limited to a single domain only with predominantly single speaker per language while the validation and test data samples are derived from diverse dataset and multiple speakers. We experiment with a neural system comprising a combination of dense, convolutional, and recurrent layers that are designed to perform better generalization and obtain speaker-invariant representations. We demonstrate that the task in its constrained form (without making use of external data or augmentation the train set with samples from the validation set) is still challenging. Our best system trained on the data augmented with validation samples achieves 29.9% accuracy on the test data.
%R 10.18653/v1/2021.sigtyp-1.14
%U https://aclanthology.org/2021.sigtyp-1.14
%U https://doi.org/10.18653/v1/2021.sigtyp-1.14
%P 145-148
Markdown (Informal)
[Anlirika: An LSTM–CNN Flow Twister for Spoken Language Identification](https://aclanthology.org/2021.sigtyp-1.14) (Scherbakov et al., SIGTYP 2021)
ACL