Sökning: "Speech-to-speech translation"

Hittade 2 uppsatser innehållade orden Speech-to-speech translation.

  1. 1. Direct Speech to Speech Translation Using Machine Learning

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Sireesh Haang Limbu; [2020]
    Nyckelord :;

    Sammanfattning : Nowadays, most of the speech to speech translation applications and services use a three step process. First step is the speech to text translation using speech recognition. This is followed by text to text language translation and finally the text is synthesized into speech. LÄS MER

  3. 2. Speech-to-speech translation using deep learning

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Fredrik Bredmar; [2017-03-17]
    Nyckelord :Neural Networks; Deep Learning; LSTM; RNN; Speech-to-speech translation;

    Sammanfattning : Current state-of-the-art translation systems for speech-to-speech rely heavily on a text representation for the translation. By transcoding speech to text we lose important information about the characteristics of the voice such as the emotion, pitch and accent. LÄS MER