@inproceedings{mishra-etal-2023-revisiting,
title = "Revisiting Automatic Speech Recognition for {T}amil and {H}indi Connected Number Recognition",
author = "Mishra, Rahul and
Gunaseela Boopathy, Senthil Raja and
Ravikiran, Manikandan and
Kulkarni, Shreyas and
Mukherjee, Mayurakshi and
Ganesh, Ananth and
Banerjee, Kingshuk",
editor = "Chakravarthi, Bharathi R. and
Priyadharshini, Ruba and
M, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth",
booktitle = "Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.dravidianlangtech-1.15",
pages = "116--123",
abstract = "Automatic Speech Recognition and its applications are rising in popularity across applications with reasonable inference results. Recent state-of-the-art approaches, often employ significantly large-scale models to show high accuracy for ASR as a whole but often do not consider detailed analysis of performance across low-resource languages applications. In this preliminary work, we propose to revisit ASR in the context of Connected Number Recognition (CNR). More specifically, we (i) present a new dataset HCNR collected to understand various errors of ASR models for CNR, (ii) establish preliminary benchmark and baseline model for CNR, (iii) explore error mitigation strategies and their after-effects on CNR. In the due process, we also compare with end-to-end large scale ASR models for reference, to show its effectiveness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mishra-etal-2023-revisiting">
<titleInfo>
<title>Revisiting Automatic Speech Recognition for Tamil and Hindi Connected Number Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senthil</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Gunaseela Boopathy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manikandan</namePart>
<namePart type="family">Ravikiran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shreyas</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mayurakshi</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ananth</namePart>
<namePart type="family">Ganesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kingshuk</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Speech Recognition and its applications are rising in popularity across applications with reasonable inference results. Recent state-of-the-art approaches, often employ significantly large-scale models to show high accuracy for ASR as a whole but often do not consider detailed analysis of performance across low-resource languages applications. In this preliminary work, we propose to revisit ASR in the context of Connected Number Recognition (CNR). More specifically, we (i) present a new dataset HCNR collected to understand various errors of ASR models for CNR, (ii) establish preliminary benchmark and baseline model for CNR, (iii) explore error mitigation strategies and their after-effects on CNR. In the due process, we also compare with end-to-end large scale ASR models for reference, to show its effectiveness.</abstract>
<identifier type="citekey">mishra-etal-2023-revisiting</identifier>
<location>
<url>https://aclanthology.org/2023.dravidianlangtech-1.15</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>116</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Automatic Speech Recognition for Tamil and Hindi Connected Number Recognition
%A Mishra, Rahul
%A Gunaseela Boopathy, Senthil Raja
%A Ravikiran, Manikandan
%A Kulkarni, Shreyas
%A Mukherjee, Mayurakshi
%A Ganesh, Ananth
%A Banerjee, Kingshuk
%Y Chakravarthi, Bharathi R.
%Y Priyadharshini, Ruba
%Y M, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%S Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F mishra-etal-2023-revisiting
%X Automatic Speech Recognition and its applications are rising in popularity across applications with reasonable inference results. Recent state-of-the-art approaches, often employ significantly large-scale models to show high accuracy for ASR as a whole but often do not consider detailed analysis of performance across low-resource languages applications. In this preliminary work, we propose to revisit ASR in the context of Connected Number Recognition (CNR). More specifically, we (i) present a new dataset HCNR collected to understand various errors of ASR models for CNR, (ii) establish preliminary benchmark and baseline model for CNR, (iii) explore error mitigation strategies and their after-effects on CNR. In the due process, we also compare with end-to-end large scale ASR models for reference, to show its effectiveness.
%U https://aclanthology.org/2023.dravidianlangtech-1.15
%P 116-123
Markdown (Informal)
[Revisiting Automatic Speech Recognition for Tamil and Hindi Connected Number Recognition](https://aclanthology.org/2023.dravidianlangtech-1.15) (Mishra et al., DravidianLangTech-WS 2023)
ACL
- Rahul Mishra, Senthil Raja Gunaseela Boopathy, Manikandan Ravikiran, Shreyas Kulkarni, Mayurakshi Mukherjee, Ananth Ganesh, and Kingshuk Banerjee. 2023. Revisiting Automatic Speech Recognition for Tamil and Hindi Connected Number Recognition. In Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages, pages 116–123, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.