@inproceedings{r-etal-2024-shot,
title = "A Few-Shot Multi-Accented Speech Classification for {I}ndian Languages using Transformers and {LLM}{'}s Fine-Tuning Approaches",
author = "R, Jairam and
G, Jyothish and
B, Premjith",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Nadarajan, Rajeswari and
Ravikiran, Manikandan",
booktitle = "Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.dravidianlangtech-1.1",
pages = "1--9",
abstract = "Accented speech classification plays a vital role in the advancement of high-quality automatic speech recognition (ASR) technology. For certain applications, like multi-accented speech classification, it is not always viable to obtain data with accent variation, especially for resource-poor languages. This is one of the major reasons that contributes to the underperformance of the speech classification systems. Therefore, in order to handle speech variability in Indian language speaker accents, we propose a few-shot learning paradigm in this study. It learns generic feature embeddings using an encoder from a pre-trained whisper model and a classification head for classification. The model is refined using LLM{'}s fine-tuning techniques, such as LoRA and QLoRA, for the six Indian English accents in the Indic Accent Dataset. The experimental findings show that the accuracy of the model is greatly increased by the few-shot learning paradigm{'}s effectiveness combined with LLM{'}s fine-tuning techniques. In optimal settings, the model{'}s accuracy can reach 94{\%} when the trainable parameters are set to 5{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="r-etal-2024-shot">
<titleInfo>
<title>A Few-Shot Multi-Accented Speech Classification for Indian Languages using Transformers and LLM’s Fine-Tuning Approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jairam</namePart>
<namePart type="family">R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyothish</namePart>
<namePart type="family">G</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Premjith</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</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">Madasamy</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>
<name type="personal">
<namePart type="given">Rajeswari</namePart>
<namePart type="family">Nadarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manikandan</namePart>
<namePart type="family">Ravikiran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Accented speech classification plays a vital role in the advancement of high-quality automatic speech recognition (ASR) technology. For certain applications, like multi-accented speech classification, it is not always viable to obtain data with accent variation, especially for resource-poor languages. This is one of the major reasons that contributes to the underperformance of the speech classification systems. Therefore, in order to handle speech variability in Indian language speaker accents, we propose a few-shot learning paradigm in this study. It learns generic feature embeddings using an encoder from a pre-trained whisper model and a classification head for classification. The model is refined using LLM’s fine-tuning techniques, such as LoRA and QLoRA, for the six Indian English accents in the Indic Accent Dataset. The experimental findings show that the accuracy of the model is greatly increased by the few-shot learning paradigm’s effectiveness combined with LLM’s fine-tuning techniques. In optimal settings, the model’s accuracy can reach 94% when the trainable parameters are set to 5%.</abstract>
<identifier type="citekey">r-etal-2024-shot</identifier>
<location>
<url>https://aclanthology.org/2024.dravidianlangtech-1.1</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Few-Shot Multi-Accented Speech Classification for Indian Languages using Transformers and LLM’s Fine-Tuning Approaches
%A R, Jairam
%A G, Jyothish
%A B, Premjith
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Nadarajan, Rajeswari
%Y Ravikiran, Manikandan
%S Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F r-etal-2024-shot
%X Accented speech classification plays a vital role in the advancement of high-quality automatic speech recognition (ASR) technology. For certain applications, like multi-accented speech classification, it is not always viable to obtain data with accent variation, especially for resource-poor languages. This is one of the major reasons that contributes to the underperformance of the speech classification systems. Therefore, in order to handle speech variability in Indian language speaker accents, we propose a few-shot learning paradigm in this study. It learns generic feature embeddings using an encoder from a pre-trained whisper model and a classification head for classification. The model is refined using LLM’s fine-tuning techniques, such as LoRA and QLoRA, for the six Indian English accents in the Indic Accent Dataset. The experimental findings show that the accuracy of the model is greatly increased by the few-shot learning paradigm’s effectiveness combined with LLM’s fine-tuning techniques. In optimal settings, the model’s accuracy can reach 94% when the trainable parameters are set to 5%.
%U https://aclanthology.org/2024.dravidianlangtech-1.1
%P 1-9
Markdown (Informal)
[A Few-Shot Multi-Accented Speech Classification for Indian Languages using Transformers and LLM’s Fine-Tuning Approaches](https://aclanthology.org/2024.dravidianlangtech-1.1) (R et al., DravidianLangTech-WS 2024)
ACL