@inproceedings{bedyakin-mikhaylovskiy-2021-language,
title = "Language {ID} Prediction from Speech Using Self-Attentive Pooling",
author = "Bedyakin, Roman and
Mikhaylovskiy, Nikolay",
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-1.12",
doi = "10.18653/v1/2021.sigtyp-1.12",
pages = "130--135",
abstract = "This memo describes NTR-TSU submission for SIGTYP 2021 Shared Task on predicting language IDs from speech. Spoken Language Identification (LID) is an important step in a multilingual Automated Speech Recognition (ASR) system pipeline. For many low-resource and endangered languages, only single-speaker recordings may be available, demanding a need for domain and speaker-invariant language ID systems. In this memo, we show that a convolutional neural network with a Self-Attentive Pooling layer shows promising results for the language identification task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bedyakin-mikhaylovskiy-2021-language">
<titleInfo>
<title>Language ID Prediction from Speech Using Self-Attentive Pooling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Bedyakin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolay</namePart>
<namePart type="family">Mikhaylovskiy</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>This memo describes NTR-TSU submission for SIGTYP 2021 Shared Task on predicting language IDs from speech. Spoken Language Identification (LID) is an important step in a multilingual Automated Speech Recognition (ASR) system pipeline. For many low-resource and endangered languages, only single-speaker recordings may be available, demanding a need for domain and speaker-invariant language ID systems. In this memo, we show that a convolutional neural network with a Self-Attentive Pooling layer shows promising results for the language identification task.</abstract>
<identifier type="citekey">bedyakin-mikhaylovskiy-2021-language</identifier>
<identifier type="doi">10.18653/v1/2021.sigtyp-1.12</identifier>
<location>
<url>https://aclanthology.org/2021.sigtyp-1.12</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>130</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language ID Prediction from Speech Using Self-Attentive Pooling
%A Bedyakin, Roman
%A Mikhaylovskiy, Nikolay
%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 bedyakin-mikhaylovskiy-2021-language
%X This memo describes NTR-TSU submission for SIGTYP 2021 Shared Task on predicting language IDs from speech. Spoken Language Identification (LID) is an important step in a multilingual Automated Speech Recognition (ASR) system pipeline. For many low-resource and endangered languages, only single-speaker recordings may be available, demanding a need for domain and speaker-invariant language ID systems. In this memo, we show that a convolutional neural network with a Self-Attentive Pooling layer shows promising results for the language identification task.
%R 10.18653/v1/2021.sigtyp-1.12
%U https://aclanthology.org/2021.sigtyp-1.12
%U https://doi.org/10.18653/v1/2021.sigtyp-1.12
%P 130-135
Markdown (Informal)
[Language ID Prediction from Speech Using Self-Attentive Pooling](https://aclanthology.org/2021.sigtyp-1.12) (Bedyakin & Mikhaylovskiy, SIGTYP 2021)
ACL