Translatotron, however, skips the text part of this process altogether and instead converts the speech into a spectrogram, an image that depicts audio frequencies.
They then translate the transcription into the target language, before finally generating audio of the translated speech. Streamlined SpeechĪccording to Google's AI blog, most speech-to-speech translation systems follow a three-step process. In other words, the tech could make it sound like you're speaking a language you don't know - a remarkable step forward on the path to breaking down the global language barrier. It's not the first system to translate speech from one language to another, but Google designed Translatotron to do something other systems can't: retain the original speaker's voice in the translated audio. On Wednesday, Google unveiled Translatotron, an in-development speech-to-speech translation system. It's designed to retain your voice and cadence in translated audio.
