LIMMITS'24: Multi-Speaker, Multi-Lingual INDIC TTS With Voice Cloning

Sathvik Udupa; Jesuraja Bandekar; Abhayjeet Singh; G. Deekshitha; Saurabh Kumar; Sandhya Badiger; Amala Nagireddi; R. Roopa; Prasanta Kumar Ghosh; Hema A. Murthy; Pranaw Kumar; Keiichi Tokuda; Mark Hasegawa-Johnson; Philipp Olbrich

doi:10.1109/OJSP.2025.3531782

LIMMITS'24: Multi-Speaker, Multi-Lingual INDIC TTS With Voice Cloning

Sathvik Udupa, Jesuraja Bandekar, Abhayjeet Singh, G. Deekshitha, Saurabh Kumar, Sandhya Badiger, Amala Nagireddi, R. Roopa, Prasanta Kumar Ghosh, Hema A. Murthy, Pranaw Kumar, Keiichi Tokuda, Mark Hasegawa-Johnson, Philipp Olbrich

Research output: Contribution to journal › Article › peer-review

Abstract

The Multi-speaker, Multi-lingual Indic Text to Speech (TTS) with voice cloning (LIMMITS'24) challenge is organized as part of the ICASSP 2024 signal processing grand challenge. LIMMITS'24 aims at the development of voice cloning for the multi-speaker, multi-lingual Text-to-Speech (TTS) model. Towards this, 80 hours of TTS data has been released in each of Bengali, Chhattisgarhi, English (Indian), and Kannada languages. This is in addition to Telugu, Hindi, and Marathi data released during the LIMMITS'23 challenge. The challenge encourages the advancement of TTS in Indian Languages as well as the development of multi-speaker voice cloning techniques for TTS. The three tracks of LIMMITS'24 have provided an opportunity for various researchers and practitioners around the world to explore the state of the art in research for voice cloning with TTS.

Original language	English (US)
Pages (from-to)	293-302
Number of pages	10
Journal	IEEE Open Journal of Signal Processing
Volume	6
DOIs	https://doi.org/10.1109/OJSP.2025.3531782
State	Published - 2025

Keywords

cross-lingual synthesis
multi-lingual TTS
multi-speaker
speech synthesis
voice cloning
Speech synthesis

ASJC Scopus subject areas

Signal Processing

Online availability

10.1109/OJSP.2025.3531782

Library availability

Discover UIUC Full Text

Cite this

@article{5a345313ac08439db3487de33715c3d3,

title = "LIMMITS'24: Multi-Speaker, Multi-Lingual INDIC TTS With Voice Cloning",

abstract = "The Multi-speaker, Multi-lingual Indic Text to Speech (TTS) with voice cloning (LIMMITS'24) challenge is organized as part of the ICASSP 2024 signal processing grand challenge. LIMMITS'24 aims at the development of voice cloning for the multi-speaker, multi-lingual Text-to-Speech (TTS) model. Towards this, 80 hours of TTS data has been released in each of Bengali, Chhattisgarhi, English (Indian), and Kannada languages. This is in addition to Telugu, Hindi, and Marathi data released during the LIMMITS'23 challenge. The challenge encourages the advancement of TTS in Indian Languages as well as the development of multi-speaker voice cloning techniques for TTS. The three tracks of LIMMITS'24 have provided an opportunity for various researchers and practitioners around the world to explore the state of the art in research for voice cloning with TTS.",

keywords = "cross-lingual synthesis, multi-lingual TTS, multi-speaker, speech synthesis, voice cloning, Speech synthesis",

author = "Sathvik Udupa and Jesuraja Bandekar and Abhayjeet Singh and G. Deekshitha and Saurabh Kumar and Sandhya Badiger and Amala Nagireddi and R. Roopa and Ghosh, {Prasanta Kumar} and Murthy, {Hema A.} and Pranaw Kumar and Keiichi Tokuda and Mark Hasegawa-Johnson and Philipp Olbrich",

note = "Part of the dataset used in this challenge was supported by Deutsche Gesellschaft f\u00FCr Internationale Zusammenarbeit (GIZ) on behalf of the German Ministry for Economic Cooperation and Development. The authors thank the German Development Cooperation project \u201CFAIR Forward - AI for All\u201D for supporting data collection.",

year = "2025",

doi = "10.1109/OJSP.2025.3531782",

language = "English (US)",

volume = "6",

pages = "293--302",

journal = "IEEE Open Journal of Signal Processing",

issn = "2644-1322",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - LIMMITS'24

T2 - Multi-Speaker, Multi-Lingual INDIC TTS With Voice Cloning

AU - Udupa, Sathvik

AU - Bandekar, Jesuraja

AU - Singh, Abhayjeet

AU - Deekshitha, G.

AU - Kumar, Saurabh

AU - Badiger, Sandhya

AU - Nagireddi, Amala

AU - Roopa, R.

AU - Ghosh, Prasanta Kumar

AU - Murthy, Hema A.

AU - Kumar, Pranaw

AU - Tokuda, Keiichi

AU - Hasegawa-Johnson, Mark

AU - Olbrich, Philipp

N1 - Part of the dataset used in this challenge was supported by Deutsche Gesellschaft f\u00FCr Internationale Zusammenarbeit (GIZ) on behalf of the German Ministry for Economic Cooperation and Development. The authors thank the German Development Cooperation project \u201CFAIR Forward - AI for All\u201D for supporting data collection.

PY - 2025

Y1 - 2025

N2 - The Multi-speaker, Multi-lingual Indic Text to Speech (TTS) with voice cloning (LIMMITS'24) challenge is organized as part of the ICASSP 2024 signal processing grand challenge. LIMMITS'24 aims at the development of voice cloning for the multi-speaker, multi-lingual Text-to-Speech (TTS) model. Towards this, 80 hours of TTS data has been released in each of Bengali, Chhattisgarhi, English (Indian), and Kannada languages. This is in addition to Telugu, Hindi, and Marathi data released during the LIMMITS'23 challenge. The challenge encourages the advancement of TTS in Indian Languages as well as the development of multi-speaker voice cloning techniques for TTS. The three tracks of LIMMITS'24 have provided an opportunity for various researchers and practitioners around the world to explore the state of the art in research for voice cloning with TTS.

AB - The Multi-speaker, Multi-lingual Indic Text to Speech (TTS) with voice cloning (LIMMITS'24) challenge is organized as part of the ICASSP 2024 signal processing grand challenge. LIMMITS'24 aims at the development of voice cloning for the multi-speaker, multi-lingual Text-to-Speech (TTS) model. Towards this, 80 hours of TTS data has been released in each of Bengali, Chhattisgarhi, English (Indian), and Kannada languages. This is in addition to Telugu, Hindi, and Marathi data released during the LIMMITS'23 challenge. The challenge encourages the advancement of TTS in Indian Languages as well as the development of multi-speaker voice cloning techniques for TTS. The three tracks of LIMMITS'24 have provided an opportunity for various researchers and practitioners around the world to explore the state of the art in research for voice cloning with TTS.

KW - cross-lingual synthesis

KW - multi-lingual TTS

KW - multi-speaker

KW - speech synthesis

KW - voice cloning

KW - Speech synthesis

UR - http://www.scopus.com/inward/record.url?scp=85216625599&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85216625599&partnerID=8YFLogxK

U2 - 10.1109/OJSP.2025.3531782

DO - 10.1109/OJSP.2025.3531782

M3 - Article

AN - SCOPUS:85216625599

SN - 2644-1322

VL - 6

SP - 293

EP - 302

JO - IEEE Open Journal of Signal Processing

JF - IEEE Open Journal of Signal Processing

ER -

LIMMITS'24: Multi-Speaker, Multi-Lingual INDIC TTS With Voice Cloning

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this