# IMaSC -- ICFOSS Malayalam Speech Corpus

arXiv: https://arxiv.org/abs/2211.12796 · HTML: https://mlsanity.com/paper/2211.12796/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 23 Nov 2022.

## Builds on (most cited first, 12 of 12)

- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines](https://mlsanity.com/paper/2010.11567/) (2020)
- [CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages](https://mlsanity.com/paper/1903.11269/) (2019)
- [DiDiSpeech: A Large Scale Mandarin Speech Corpus](https://mlsanity.com/paper/2010.09275/) (2020)
- [Talking Face Generation with Multilingual TTS](https://mlsanity.com/paper/2205.06421/) (2022)
- [KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset](https://mlsanity.com/paper/2104.08459/) (2021)
- [TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese](https://mlsanity.com/paper/2005.05144/) (2020)
- [VoiceMe: Personalized voice generation in TTS](https://mlsanity.com/paper/2203.15379/) (2022)

## Built on by (most cited first, 1 of 1)

- [SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR](https://mlsanity.com/paper/2605.20712/) (2026)

## Abstract (arXiv)

Modern text-to-speech (TTS) systems use deep learning to synthesize speech increasingly approaching human quality, but they require a database of high quality audio-text sentence pairs for training. Malayalam, the official language of the Indian state of Kerala and spoken by 35+ million people, is a low resource language in terms of available corpora for TTS systems. In this paper, we present IMaSC, a Malayalam text and speech corpora containing approximately 50 hours of recorded speech. With 8 speakers and a total of 34,473 text-audio pairs, IMaSC is larger than every other publicly available alternative. We evaluated the database by using it to train TTS models for each speaker based on a modern deep learning architecture. Via subjective evaluation, we show that our models perform significantly better in terms of naturalness compared to previous studies and publicly available models, with an average mean opinion score of 4.50, indicating that the synthesized speech is close to human quality.