@inproceedings{rizvi-etal-2023-cross,
title = "Cross-Lingual Speaker Identification for {I}ndian Languages",
author = {Rizvi, Amaan and
Jamatia, Anupam and
Rudrapal, Dwijen and
Chakma, Kunal and
Gamb{\"a}ck, Bj{\"o}rn},
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-1.105",
pages = "979--987",
abstract = "The paper introduces a cross-lingual speaker identification system for Indian languages, utilising a Long Short-Term Memory dense neural network (LSTM-DNN). The system was trained on audio recordings in English and evaluated on data from Hindi, Kannada, Malayalam, Tamil, and Telugu, with a view to how factors such as phonetic similarity and native accent affect performance. The model was fed with MFCC (mel-frequency cepstral coefficient) features extracted from the audio file. For comparison, the corresponding mel-spectrogram images were also used as input to a ResNet-50 model, while the raw audio was used to train a Siamese network. The LSTM-DNN model outperformed the other two models as well as two more traditional baseline speaker identification models, showing that deep learning models are superior to probabilistic models for capturing low-level speech features and learning speaker characteristics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rizvi-etal-2023-cross">
<titleInfo>
<title>Cross-Lingual Speaker Identification for Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amaan</namePart>
<namePart type="family">Rizvi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anupam</namePart>
<namePart type="family">Jamatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dwijen</namePart>
<namePart type="family">Rudrapal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kunal</namePart>
<namePart type="family">Chakma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Björn</namePart>
<namePart type="family">Gambäck</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 14th International Conference on Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</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>The paper introduces a cross-lingual speaker identification system for Indian languages, utilising a Long Short-Term Memory dense neural network (LSTM-DNN). The system was trained on audio recordings in English and evaluated on data from Hindi, Kannada, Malayalam, Tamil, and Telugu, with a view to how factors such as phonetic similarity and native accent affect performance. The model was fed with MFCC (mel-frequency cepstral coefficient) features extracted from the audio file. For comparison, the corresponding mel-spectrogram images were also used as input to a ResNet-50 model, while the raw audio was used to train a Siamese network. The LSTM-DNN model outperformed the other two models as well as two more traditional baseline speaker identification models, showing that deep learning models are superior to probabilistic models for capturing low-level speech features and learning speaker characteristics.</abstract>
<identifier type="citekey">rizvi-etal-2023-cross</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-1.105</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>979</start>
<end>987</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Speaker Identification for Indian Languages
%A Rizvi, Amaan
%A Jamatia, Anupam
%A Rudrapal, Dwijen
%A Chakma, Kunal
%A Gambäck, Björn
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F rizvi-etal-2023-cross
%X The paper introduces a cross-lingual speaker identification system for Indian languages, utilising a Long Short-Term Memory dense neural network (LSTM-DNN). The system was trained on audio recordings in English and evaluated on data from Hindi, Kannada, Malayalam, Tamil, and Telugu, with a view to how factors such as phonetic similarity and native accent affect performance. The model was fed with MFCC (mel-frequency cepstral coefficient) features extracted from the audio file. For comparison, the corresponding mel-spectrogram images were also used as input to a ResNet-50 model, while the raw audio was used to train a Siamese network. The LSTM-DNN model outperformed the other two models as well as two more traditional baseline speaker identification models, showing that deep learning models are superior to probabilistic models for capturing low-level speech features and learning speaker characteristics.
%U https://aclanthology.org/2023.ranlp-1.105
%P 979-987
Markdown (Informal)
[Cross-Lingual Speaker Identification for Indian Languages](https://aclanthology.org/2023.ranlp-1.105) (Rizvi et al., RANLP 2023)
ACL
- Amaan Rizvi, Anupam Jamatia, Dwijen Rudrapal, Kunal Chakma, and Björn Gambäck. 2023. Cross-Lingual Speaker Identification for Indian Languages. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 979–987, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.