Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech

Abhayjeet Singh; Amala Nagireddi; G. Deekshitha; Jesuraja Bandekar; R. Roopa; Sandhya Badiger; Sathvik Udupa; Prasanta Kumar Ghosh; Hema A. Murthy; Heiga Zen; Pranaw Kumar; Kamal Kant; Amol Bole; Bira Chandra Singh; Keiichi Tokuda; Mark Hasegawa-Johnson; Philipp Olbrich

doi:10.1109/ICASSP49357.2023.10433926

Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech

Abhayjeet Singh, Amala Nagireddi, G. Deekshitha, Jesuraja Bandekar, R. Roopa, Sandhya Badiger, Sathvik Udupa, Prasanta Kumar Ghosh, Hema A. Murthy, Heiga Zen, Pranaw Kumar, Kamal Kant, Amol Bole, Bira Chandra Singh, Keiichi Tokuda, Mark Hasegawa-Johnson, Philipp Olbrich

Research output: Contribution to journal › Conference article › peer-review

Abstract

The Lightweight, Multi-speaker, Multi-lingual Indic Text-to-Speech (LIMMITS'23) challenge is organized as part of the ICASSP 2023 signal processing grand challenge. LIMMITS'23 aims at the development of a lightweight, multi-speaker, multi-lingual Text to Speech (TTS) model using datasets in Marathi, Hindi, and Telugu. The challenge encourages the advancement of TTS in Indian Languages as well as the development of techniques involved in TTS data selection and model compression. The 3 tracks of LIMMITS'23 have provided an opportunity for various researchers and practitioners around the world to explore the state of the art in TTS research.

Original language	English (US)
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
DOIs	https://doi.org/10.1109/ICASSP49357.2023.10433926
State	Published - 2023
Event	48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece Duration: Jun 4 2023 → Jun 10 2023

Keywords

Text-to-Speech (TTS)
data-constrained multi-speaker
end-to-end
model compression
multi-lingual TTS
speech synthesis

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Online availability

10.1109/ICASSP49357.2023.10433926

Library availability

Discover UIUC Full Text

Cite this

Singh, A., Nagireddi, A., Deekshitha, G., Bandekar, J., Roopa, R., Badiger, S., Udupa, S., Ghosh, P. K., Murthy, H. A., Zen, H., Kumar, P., Kant, K., Bole, A., Singh, B. C., Tokuda, K., Hasegawa-Johnson, M., & Olbrich, P. (2023). Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. https://doi.org/10.1109/ICASSP49357.2023.10433926

Singh, A, Nagireddi, A, Deekshitha, G, Bandekar, J, Roopa, R, Badiger, S, Udupa, S, Ghosh, PK, Murthy, HA, Zen, H, Kumar, P, Kant, K, Bole, A, Singh, BC, Tokuda, K, Hasegawa-Johnson, M & Olbrich, P 2023, 'Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech', ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. https://doi.org/10.1109/ICASSP49357.2023.10433926

@article{0ab02248e77040fab0be466ff39f7548,

title = "Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech",

abstract = "The Lightweight, Multi-speaker, Multi-lingual Indic Text-to-Speech (LIMMITS'23) challenge is organized as part of the ICASSP 2023 signal processing grand challenge. LIMMITS'23 aims at the development of a lightweight, multi-speaker, multi-lingual Text to Speech (TTS) model using datasets in Marathi, Hindi, and Telugu. The challenge encourages the advancement of TTS in Indian Languages as well as the development of techniques involved in TTS data selection and model compression. The 3 tracks of LIMMITS'23 have provided an opportunity for various researchers and practitioners around the world to explore the state of the art in TTS research.",

keywords = "Text-to-Speech (TTS), data-constrained multi-speaker, end-to-end, model compression, multi-lingual TTS, speech synthesis",

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

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",

year = "2023",

doi = "10.1109/ICASSP49357.2023.10433926",

language = "English (US)",

journal = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

issn = "1520-6149",

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

}

TY - JOUR

T1 - Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech

AU - Singh, Abhayjeet

AU - Nagireddi, Amala

AU - Deekshitha, G.

AU - Bandekar, Jesuraja

AU - Roopa, R.

AU - Badiger, Sandhya

AU - Udupa, Sathvik

AU - Ghosh, Prasanta Kumar

AU - Murthy, Hema A.

AU - Zen, Heiga

AU - Kumar, Pranaw

AU - Kant, Kamal

AU - Bole, Amol

AU - Singh, Bira Chandra

AU - Tokuda, Keiichi

AU - Hasegawa-Johnson, Mark

AU - Olbrich, Philipp

PY - 2023

Y1 - 2023

N2 - The Lightweight, Multi-speaker, Multi-lingual Indic Text-to-Speech (LIMMITS'23) challenge is organized as part of the ICASSP 2023 signal processing grand challenge. LIMMITS'23 aims at the development of a lightweight, multi-speaker, multi-lingual Text to Speech (TTS) model using datasets in Marathi, Hindi, and Telugu. The challenge encourages the advancement of TTS in Indian Languages as well as the development of techniques involved in TTS data selection and model compression. The 3 tracks of LIMMITS'23 have provided an opportunity for various researchers and practitioners around the world to explore the state of the art in TTS research.

AB - The Lightweight, Multi-speaker, Multi-lingual Indic Text-to-Speech (LIMMITS'23) challenge is organized as part of the ICASSP 2023 signal processing grand challenge. LIMMITS'23 aims at the development of a lightweight, multi-speaker, multi-lingual Text to Speech (TTS) model using datasets in Marathi, Hindi, and Telugu. The challenge encourages the advancement of TTS in Indian Languages as well as the development of techniques involved in TTS data selection and model compression. The 3 tracks of LIMMITS'23 have provided an opportunity for various researchers and practitioners around the world to explore the state of the art in TTS research.

KW - Text-to-Speech (TTS)

KW - data-constrained multi-speaker

KW - end-to-end

KW - model compression

KW - multi-lingual TTS

KW - speech synthesis

UR - http://www.scopus.com/inward/record.url?scp=85185222685&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85185222685&partnerID=8YFLogxK

U2 - 10.1109/ICASSP49357.2023.10433926

DO - 10.1109/ICASSP49357.2023.10433926

M3 - Conference article

AN - SCOPUS:85185222685

SN - 1520-6149

JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

T2 - 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

Y2 - 4 June 2023 through 10 June 2023

ER -

Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this