New Features: Speech Recognition and Synthesis for Private Courses in SuperMemo Mobile Apps

Speech synthesis on iOS

One of the biggest challenges for language learners is speaking properly, especially if they learn solo. Thanks to the development of speech technologies, you can now get instant feedback on your speaking and pronunciation skills while learning with private courses in SuperMemo mobile apps.

We have implemented speech synthesis for the question and answer texts so that you can listen to them and speech recognition for the answers, so you can respond by speaking, making sure that your pronunciation is understandable and correct. All of the languages available in the speech settings of your smartphone can be applied. You can use different languages for different MemoCards in the same course. You can even exclude parts of the text from synthesis and recognition by marking them with square brackets.

Benefits of using speech recognition for language learning

  • Speech recognition can help you improve your pronunciation
  • Talking to a mobile device is not intimidating. You won’t be embarrassed if you make some mistakes. You can retry as many times as you wish, to achieve perfection
  • Learning with an app provides flexibility. There is no need to schedule time with a teacher or conversation partner
  • You save time – speaking is quicker and more convenient than typing

How to set the speech features in SuperMemo

  • Enter any private course (or MemoCards) in your SuperMemo mobile app.
  • Tap the menu icon and select “Speech Settings”.
  • In the new window switch the “play the question/answer” option on and pick the language/-s to be used to read the questions and/or answers in your course.
  • Decide whether to apply the settings to just one card or the entire course, then confirm with Save.
  • You can change these settings at any time.
  • Note that, depending on the device, Internet access may be necessary in order to use the speech features.

How to use the speech features in SuperMemo

  • Speech is generated automatically for MemoCards set as above.
  • You can repeat the audio simply by tapping the text you want to hear.
  • While in answer mode, tap the microphone icon to start recognizing your speech. The recording ends automatically after a moment of silence. The recognized text appears next to the microphone.
  • You can remove the recognized text from the screen by moving it aside.
  • If you would like to exclude part of the text from the speech synthesis or recognition, simply place it in square brackets.