Navigation


Myanmar Automatic Speech Recognition Version 1.0

Contributed by ASR team: Professor Dr. Win Pa Pa

Aye Nyein Mon

Aye Mya Hlaing

Myat Aye Aye Aung


This Myanmar Automatic Speech Recognition (Speech-to-Text) version 1.0 is working very well on Myanmar read News, like MRTV, MRTV-4 news.

How to use: Record your voice via mobile phone or recording device and upload the file here.

မိုဘိုင်းလ်ဖုန်း သို့မဟုတ် အသံသွင်းကိရိယာ ဖြင့် အသံသွင်းထားသော အသံဖိုင် ကို အောက်ဖော်ပြပါ နေရာတွင် ရွေးချယ်ပါ ။


Upload an utterance file :

* in .mp3 or .wav format

* not larger than 2MB


audio file format (*.wma, *.flac, *.m4a, *.amr, *.ogg, *.oga, *.mid, *.midi, *.rmi, *.aiff) မှ .wav file format သို့ ဤနေရာတွင် ပြောင်းလဲနိုင်ပါသည် ။


The transcription of your speech will be recognized and shown in the following box.

အသံမှ စာသားသို့ ပြောင်းထားသော အဖြေကို အောက်တွင် ဖော်ပြထားပါသည် ။


Recognized Myanmar Text

Unicode Encoding ဖြင့် မှန်ကန်စွာ ကြည့်ရှုနိုင်ပါသည် ။

Automatic speech recognition is a very useful to many application areas such as

  • Automatic subtitling
  • Automatic translation
  • Real time Speech writing
  • User interface for hands-free computing e.g. typing by speech
  • Interactive voice response
  • Home automation
  • Mobile telephony
  • Real time Captioning
  • Robotics
  • Transcription

Publications

1. Aye Nyein Mon, Win Pa Pa, Ye Kyaw Thu and Yoshinori Sagisaka, "Developing a Speech Corpus from Web News for Myanmar (Burmese) Language", In Proceedings of The 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (Oriental COCOSDA 2017), November 1-3, 2017, Seoul National University Hoam Faculty House, Convention center, Seoul, R.O. Korea, pp. 75-80[paper]

2. Aye Nyein Mon, Win Pa Pa, and Ye Kyaw Thu,"Exploring the Effect of Tones for Myanmar Language Speech Recognition Using Convolutional Neural Network (CNN)", In Proceedings of 15th International Conference of the Pacific Association for Computational Linguistics (PACLING), 2017, Yangon, Myanmar, pp. 334-345.[paper]

3. Aye Nyein Mon, Win Pa Pa, Ye Kyaw Thu, "Building HMM-SGMM Continuous Automatic Speech Recognition on Myanmar Web News". The Proceedings of 15th International Conference on Computer Application(ICCA2017), pages 446-453. Yangon, Myanmar, 16-17 February

4. Myat Aye Aye Aung, Win Pa Pa, "Analysis of Feature Extraction Techniques for Myanmar Automatic Speech Recognition". M.C.Sc (Thesis) dissertation, University of Computer Studies, Yangon, February 2018.


Updated on 20.12.2018