<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sadeq-etal-2020-improving">
    <titleInfo>
        <title>Improving End-to-End Bangla Speech Recognition with Semi-supervised Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nafis</namePart>
        <namePart type="family">Sadeq</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nafis</namePart>
        <namePart type="given">Tahmid</namePart>
        <namePart type="family">Chowdhury</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Farhan</namePart>
        <namePart type="given">Tanvir</namePart>
        <namePart type="family">Utshaw</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shafayat</namePart>
        <namePart type="family">Ahmed</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="given">Abdullah</namePart>
        <namePart type="family">Adnan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</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>Automatic speech recognition systems usually require large annotated speech corpus for training. The manual annotation of a large corpus is very difficult. It can be very helpful to use unsupervised and semi-supervised learning methods in addition to supervised learning. In this work, we focus on using a semi-supervised training approach for Bangla Speech Recognition that can exploit large unpaired audio and text data. We encode speech and text data in an intermediate domain and propose a novel loss function based on the global encoding distance between encoded data to guide the semi-supervised training. Our proposed method reduces the Word Error Rate (WER) of the system from 37% to 31.9%.</abstract>
    <identifier type="citekey">sadeq-etal-2020-improving</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.169</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.169</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>1875</start>
            <end>1883</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving End-to-End Bangla Speech Recognition with Semi-supervised Training
%A Sadeq, Nafis
%A Chowdhury, Nafis Tahmid
%A Utshaw, Farhan Tanvir
%A Ahmed, Shafayat
%A Adnan, Muhammad Abdullah
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F sadeq-etal-2020-improving
%X Automatic speech recognition systems usually require large annotated speech corpus for training. The manual annotation of a large corpus is very difficult. It can be very helpful to use unsupervised and semi-supervised learning methods in addition to supervised learning. In this work, we focus on using a semi-supervised training approach for Bangla Speech Recognition that can exploit large unpaired audio and text data. We encode speech and text data in an intermediate domain and propose a novel loss function based on the global encoding distance between encoded data to guide the semi-supervised training. Our proposed method reduces the Word Error Rate (WER) of the system from 37% to 31.9%.
%R 10.18653/v1/2020.findings-emnlp.169
%U https://aclanthology.org/2020.findings-emnlp.169
%U https://doi.org/10.18653/v1/2020.findings-emnlp.169
%P 1875-1883

Markdown (Informal)

[Improving End-to-End Bangla Speech Recognition with Semi-supervised Training](https://aclanthology.org/2020.findings-emnlp.169) (Sadeq et al., Findings 2020)

• Improving End-to-End Bangla Speech Recognition with Semi-supervised Training (Sadeq et al., Findings 2020)

ACL

• Nafis Sadeq, Nafis Tahmid Chowdhury, Farhan Tanvir Utshaw, Shafayat Ahmed, and Muhammad Abdullah Adnan. 2020. Improving End-to-End Bangla Speech Recognition with Semi-supervised Training. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1875–1883, Online. Association for Computational Linguistics.