IndicSpeech: Text-to-Speech Corpus for Indian Languages

 

  [Dataset]word

Word clouds of the collected corpus for 3 languages

Abstract

India is a country where several tens of languages are spoken by over a billion strong population. Text-to-speech systems for such languages will thus be extremely beneficial for wide-spread content creation and accessibility. Despite this, the current TTS systems for even the most popular Indian languages fall short of the contemporary state-of-the-art systems for English, Chinese, etc. We believe that one of the major reasons for this is the lack of large, publicly available text-to-speech corpora in these languages that are suitable for training neural text-to-speech systems. To mitigate this, we release a large text-to-speech corpus for $3$ major Indian languages namely Hindi, Malayalam and Bengali. In this work, we also train a state-of-the-art TTS system for each of these languages and report their performances.


Paper

  • IndicSpeech: Text-to-Speech Corpus for Indian Languages

    Nimisha Srivastava, Rudrabha Mukhopadhyay*, Prajwal K R*, C.V. Jawahar
    IndicSpeech: Text-to-Speech Corpus for Indian Languages, LREC, 2020 
    [PDF] |

    @inproceedings{srivastava-etal-2020-indicspeech,
    title = "{I}ndic{S}peech: Text-to-Speech Corpus for {I}ndian Languages",
    author = "Srivastava, Nimisha and
    Mukhopadhyay, Rudrabha and
    K R, Prajwal and
    Jawahar, C V",
    booktitle = "Proceedings of The 12th Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://www.aclweb.org/anthology/2020.lrec-1.789",
    pages = "6417--6422",
    abstract = "India is a country where several tens of languages are spoken by over a billion strong population. Text-to-speech systems for such languages will thus be extremely beneficial for wide-spread content creation and accessibility. Despite this, the current TTS systems for even the most popular Indian languages fall short of the contemporary state-of-the-art systems for English, Chinese, etc. We believe that one of the major reasons for this is the lack of large, publicly available text-to-speech corpora in these languages that are suitable for training neural text-to-speech systems. To mitigate this, we release a 24 hour text-to-speech corpus for 3 major Indian languages namely Hindi, Malayalam and Bengali. In this work, we also train a state-of-the-art TTS system for each of these languages and report their performances. The collected corpus, code, and trained models are made publicly available.",
    language = "English",
    ISBN = "979-10-95546-34-4",
    }

Live Demo

Please click here for demo video : https://bhaasha.iiit.ac.in/indic-tts/


Contact

  1. Prajwal K R - This email address is being protected from spambots. You need JavaScript enabled to view it.
  2. Rudrabha Mukhopadhyay - This email address is being protected from spambots. You need JavaScript enabled to view it.