@inproceedings{bansal-2020-acoustic,
title = "Acoustic-Phonetic Approach for {ASR} of Less Resourced Languages Using Monolingual and Cross-Lingual Information",
author = "Bansal, Shweta",
editor = "Beermann, Dorothee and
Besacier, Laurent and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources association",
url = "https://aclanthology.org/2020.sltu-1.23",
pages = "167--171",
abstract = "The exploration of speech processing for endangered languages has substantially increased in the past epoch of time. In this paper, we present the acoustic-phonetic approach for automatic speech recognition (ASR) using monolingual and cross-lingual information with application to under-resourced Indian languages, Punjabi, Nepali and Hindi. The challenging task while developing the ASR was the collection of the acoustic corpus for under-resourced languages. We have described here, in brief, the strategies used for designing the corpus and also highlighted the issues pertaining while collecting data for these languages. The bootstrap GMM-UBM based approach is used, which integrates pronunciation lexicon, language model and acoustic-phonetic model. Mel Frequency Cepstral Coefficients were used for extracting the acoustic signal features for training in monolingual and cross-lingual settings. The experimental result shows the overall performance of ASR for cross-lingual and monolingual. The phone substitution plays a key role in the cross-lingual as well as monolingual recognition. The result obtained by cross-lingual recognition compared with other baseline system and it has been found that the performance of the recognition system is based on phonemic units . The recognition rate of cross-lingual generally declines as compared with the monolingual.",
language = "English",
ISBN = "979-10-95546-35-1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bansal-2020-acoustic">
<titleInfo>
<title>Acoustic-Phonetic Approach for ASR of Less Resourced Languages Using Monolingual and Cross-Lingual Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shweta</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-35-1</identifier>
</relatedItem>
<abstract>The exploration of speech processing for endangered languages has substantially increased in the past epoch of time. In this paper, we present the acoustic-phonetic approach for automatic speech recognition (ASR) using monolingual and cross-lingual information with application to under-resourced Indian languages, Punjabi, Nepali and Hindi. The challenging task while developing the ASR was the collection of the acoustic corpus for under-resourced languages. We have described here, in brief, the strategies used for designing the corpus and also highlighted the issues pertaining while collecting data for these languages. The bootstrap GMM-UBM based approach is used, which integrates pronunciation lexicon, language model and acoustic-phonetic model. Mel Frequency Cepstral Coefficients were used for extracting the acoustic signal features for training in monolingual and cross-lingual settings. The experimental result shows the overall performance of ASR for cross-lingual and monolingual. The phone substitution plays a key role in the cross-lingual as well as monolingual recognition. The result obtained by cross-lingual recognition compared with other baseline system and it has been found that the performance of the recognition system is based on phonemic units . The recognition rate of cross-lingual generally declines as compared with the monolingual.</abstract>
<identifier type="citekey">bansal-2020-acoustic</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.23</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>167</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Acoustic-Phonetic Approach for ASR of Less Resourced Languages Using Monolingual and Cross-Lingual Information
%A Bansal, Shweta
%Y Beermann, Dorothee
%Y Besacier, Laurent
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
%D 2020
%8 May
%I European Language Resources association
%C Marseille, France
%@ 979-10-95546-35-1
%G English
%F bansal-2020-acoustic
%X The exploration of speech processing for endangered languages has substantially increased in the past epoch of time. In this paper, we present the acoustic-phonetic approach for automatic speech recognition (ASR) using monolingual and cross-lingual information with application to under-resourced Indian languages, Punjabi, Nepali and Hindi. The challenging task while developing the ASR was the collection of the acoustic corpus for under-resourced languages. We have described here, in brief, the strategies used for designing the corpus and also highlighted the issues pertaining while collecting data for these languages. The bootstrap GMM-UBM based approach is used, which integrates pronunciation lexicon, language model and acoustic-phonetic model. Mel Frequency Cepstral Coefficients were used for extracting the acoustic signal features for training in monolingual and cross-lingual settings. The experimental result shows the overall performance of ASR for cross-lingual and monolingual. The phone substitution plays a key role in the cross-lingual as well as monolingual recognition. The result obtained by cross-lingual recognition compared with other baseline system and it has been found that the performance of the recognition system is based on phonemic units . The recognition rate of cross-lingual generally declines as compared with the monolingual.
%U https://aclanthology.org/2020.sltu-1.23
%P 167-171
Markdown (Informal)
[Acoustic-Phonetic Approach for ASR of Less Resourced Languages Using Monolingual and Cross-Lingual Information](https://aclanthology.org/2020.sltu-1.23) (Bansal, SLTU 2020)
ACL