@inproceedings{regmi-bal-2021-end,
title = "An End-to-End Speech Recognition for the {N}epali Language",
author = "Regmi, Sunil and
Bal, Bal Krishna",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.22/",
pages = "180--185",
abstract = "In this era of AI and Deep Learning, Speech Recognition has achieved fairly good levels of accuracy and is bound to change the way humans interact with computers, which happens mostly through texts today. Most of the speech recognition systems for the Nepali language to date use conventional approaches which involve separately trained acoustic, pronunciation and language model components. Creating a pronunciation lexicon from scratch and defining phoneme sets for the language requires expert knowledge, and at the same time is time-consuming. In this work, we present an End-to-End ASR approach, which uses a joint CTC- attention-based encoder-decoder and a Recurrent Neural Network based language modeling which eliminates the need of creating a pronunciation lexicon from scratch. ESPnet toolkit which uses Kaldi Style of data preparation is the framework used for this work. The speech and transcription data used for this research is freely available on the Open Speech and Language Resources (OpenSLR). We use about 159k transcribed speech data to train the speech recognition model which currently recognizes speech input with the CER of 10.3{\%}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="regmi-bal-2021-end">
<titleInfo>
<title>An End-to-End Speech Recognition for the Nepali Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Regmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this era of AI and Deep Learning, Speech Recognition has achieved fairly good levels of accuracy and is bound to change the way humans interact with computers, which happens mostly through texts today. Most of the speech recognition systems for the Nepali language to date use conventional approaches which involve separately trained acoustic, pronunciation and language model components. Creating a pronunciation lexicon from scratch and defining phoneme sets for the language requires expert knowledge, and at the same time is time-consuming. In this work, we present an End-to-End ASR approach, which uses a joint CTC- attention-based encoder-decoder and a Recurrent Neural Network based language modeling which eliminates the need of creating a pronunciation lexicon from scratch. ESPnet toolkit which uses Kaldi Style of data preparation is the framework used for this work. The speech and transcription data used for this research is freely available on the Open Speech and Language Resources (OpenSLR). We use about 159k transcribed speech data to train the speech recognition model which currently recognizes speech input with the CER of 10.3%.</abstract>
<identifier type="citekey">regmi-bal-2021-end</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.22/</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>180</start>
<end>185</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An End-to-End Speech Recognition for the Nepali Language
%A Regmi, Sunil
%A Bal, Bal Krishna
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F regmi-bal-2021-end
%X In this era of AI and Deep Learning, Speech Recognition has achieved fairly good levels of accuracy and is bound to change the way humans interact with computers, which happens mostly through texts today. Most of the speech recognition systems for the Nepali language to date use conventional approaches which involve separately trained acoustic, pronunciation and language model components. Creating a pronunciation lexicon from scratch and defining phoneme sets for the language requires expert knowledge, and at the same time is time-consuming. In this work, we present an End-to-End ASR approach, which uses a joint CTC- attention-based encoder-decoder and a Recurrent Neural Network based language modeling which eliminates the need of creating a pronunciation lexicon from scratch. ESPnet toolkit which uses Kaldi Style of data preparation is the framework used for this work. The speech and transcription data used for this research is freely available on the Open Speech and Language Resources (OpenSLR). We use about 159k transcribed speech data to train the speech recognition model which currently recognizes speech input with the CER of 10.3%.
%U https://aclanthology.org/2021.icon-main.22/
%P 180-185
Markdown (Informal)
[An End-to-End Speech Recognition for the Nepali Language](https://aclanthology.org/2021.icon-main.22/) (Regmi & Bal, ICON 2021)
ACL
- Sunil Regmi and Bal Krishna Bal. 2021. An End-to-End Speech Recognition for the Nepali Language. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 180–185, National Institute of Technology Silchar, Silchar, India. NLP Association of India (NLPAI).