Integration of Real-Time Speech Processing Technologies for Online Gaming

This work demonstrates an application of different real-time speech technologies, exploited in an online gaming scenario. The game developed for this purpose is inspired by the famous television based quiz-game show, “Who wants to be a millionaire”, in which multiple-choice questions of increasing difficulty are asked to the participant. Text-to-speech synthesis is used to read out the questions and the possible answers to the user, while an automatic speech recognition engine is exploited to get input from the player, in order to proceed through the game. The speech data is recorded from the user with the help of a real-time voice activity detector to select speech segments from the input audio data. The developed Java application allows an automatic insertion of new multiple-choice questions, of different complexity, which could then be selected during the game.

    Keywords: ASR ; gaming ; TTS


    • EPFL-REPORT-217480

    Record created on 2016-03-19, modified on 2016-08-09

Related material