AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
Google translate voice coverter4/2/2024 Translatotron is currently a proof of concept. Not only does this approach produce more nuanced translations by retaining important nonverbal cues, but in theory it should also minimize translation error, because it reduces the task to fewer steps. The third component can then layer the original speaker’s vocal characteristics back into the final audio output. The second converts the spectrogram into an audio wave that can be played. The first component uses a neural network trained to map the audio spectrogram in the input language to the audio spectrogram in the output language. The new system, dubbed the Translatotron, has three components, all of which look at the speaker’s audio spectrogram-a visual snapshot of the frequencies used when the sound is playing, often called a voiceprint. In contrast, traditional translational systems convert audio into text, translate the text, and then resynthesize the audio, losing the characteristics of the original voice along the way. It can do this because it converts audio input directly to audio output without any intermediary steps. The results aren’t perfect, but you can sort of hear how Google’s translator was able to retain the voice and tone of the original speaker. Now this is how it sounds when put through Google’s new automated translation system. This is how its English translation might sound when put through a traditional automated translation system.
0 Comments
Read More
Leave a Reply. |