@inproceedings{mirishkar-etal-2021-investigation,
title = "An Investigation of Hybrid architectures for Low Resource Multilingual Speech Recognition system in {I}ndian context",
author = "Mirishkar, Ganesh and
Yadavalli, Aditya and
Vuppala, Anil Kumar",
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.25",
pages = "205--212",
abstract = "India is a land of language diversity. There are approximately 2000 languages spoken around, and among which officially registered are 23. In those, there are very few with Automatic Speech Recognition (ASR) capability. The reason for this is the fact that building an ASR system requires thousands of hours of annotated speech data, a vast amount of text, and a lexicon that can span all the words in the language. At the same time, it is observed that Indian languages share a common phonetic base. In this work, we build a multilingual speech recognition system for low-resource languages by leveraging the shared phonetic space. Deep Neural architectures play a vital role in improving the performance of low-resource ASR systems. The typical strategy used to train the multilingual acoustic model is merging various languages as a unified group. In this paper, the speech recognition system is built using six Indian languages, namely Gujarati, Hindi, Marathi, Odia, Tamil, and Telugu. Various state-of-the-art experiments were performed using different acoustic modeling and language modeling techniques.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mirishkar-etal-2021-investigation">
<titleInfo>
<title>An Investigation of Hybrid architectures for Low Resource Multilingual Speech Recognition system in Indian context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ganesh</namePart>
<namePart type="family">Mirishkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Yadavalli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anil</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Vuppala</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>India is a land of language diversity. There are approximately 2000 languages spoken around, and among which officially registered are 23. In those, there are very few with Automatic Speech Recognition (ASR) capability. The reason for this is the fact that building an ASR system requires thousands of hours of annotated speech data, a vast amount of text, and a lexicon that can span all the words in the language. At the same time, it is observed that Indian languages share a common phonetic base. In this work, we build a multilingual speech recognition system for low-resource languages by leveraging the shared phonetic space. Deep Neural architectures play a vital role in improving the performance of low-resource ASR systems. The typical strategy used to train the multilingual acoustic model is merging various languages as a unified group. In this paper, the speech recognition system is built using six Indian languages, namely Gujarati, Hindi, Marathi, Odia, Tamil, and Telugu. Various state-of-the-art experiments were performed using different acoustic modeling and language modeling techniques.</abstract>
<identifier type="citekey">mirishkar-etal-2021-investigation</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.25</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>205</start>
<end>212</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Investigation of Hybrid architectures for Low Resource Multilingual Speech Recognition system in Indian context
%A Mirishkar, Ganesh
%A Yadavalli, Aditya
%A Vuppala, Anil Kumar
%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 mirishkar-etal-2021-investigation
%X India is a land of language diversity. There are approximately 2000 languages spoken around, and among which officially registered are 23. In those, there are very few with Automatic Speech Recognition (ASR) capability. The reason for this is the fact that building an ASR system requires thousands of hours of annotated speech data, a vast amount of text, and a lexicon that can span all the words in the language. At the same time, it is observed that Indian languages share a common phonetic base. In this work, we build a multilingual speech recognition system for low-resource languages by leveraging the shared phonetic space. Deep Neural architectures play a vital role in improving the performance of low-resource ASR systems. The typical strategy used to train the multilingual acoustic model is merging various languages as a unified group. In this paper, the speech recognition system is built using six Indian languages, namely Gujarati, Hindi, Marathi, Odia, Tamil, and Telugu. Various state-of-the-art experiments were performed using different acoustic modeling and language modeling techniques.
%U https://aclanthology.org/2021.icon-main.25
%P 205-212
Markdown (Informal)
[An Investigation of Hybrid architectures for Low Resource Multilingual Speech Recognition system in Indian context](https://aclanthology.org/2021.icon-main.25) (Mirishkar et al., ICON 2021)
ACL