|
|
[br]
[br][br]For years, we have been using Google Translate (among other tools) as a way to convert spoken sentences in one language to another.[br][br]The technology works pretty well, but now, Google is pushing it forward with what it calls project 'Translatotron'.[br][br]It is an AI-based system that directly translates speech into speech while retaining the vocal characteristics of the speaker.[br][br]Here's what it means.[br][br]Conventional translation involves text[br][br][br][br]If you have used Google Translate or any other voice translation tool, you must already know that the current translation systems involve multiple layers.[br][br]The words you speak are first recognized and converted into text, then that text is converted into the language you prefer, and finally, the converted text is synthesized as a vocal output, which sounds like a robot speaking.[br][br]Now, Google is bringing 'Translatotron'[br][br]In a bid to make this 'multi-layered' process simpler, Google has announced its experimental Translatotron system.[br][br]The company says that the tech uses machine learning to convert words and sentences spoken in one language into another language without involving texts in between.[br][br]This, naturally, makes the translation process faster and reduces the risk of errors that could occur in multi-step translation[br][br]How AI translates speech into speech directly[br][br]After working on the idea of speech-to-speech translation for years, Google brought Translatotron to life by converting spectrograms of speech in one language to spectrograms in another, using machine learning algorithms.[br][br]For the uninitiated, spectrograms are detailed frequency breakdowns of audio as it varies with time; they are also dubbed as sonographs, voiceprints, or voicegrams.[br][br]These spectrograms help the system with direct translation[br][br][br]Plus, it retains the vocal characteristics of the speaker[br][br]The process, as we said, is faster than the conventional technique, but more importantly, it comes with the element of expression.[br][br]Essentially, the system relies on a neural vocoder and speaker encoder, which helps the system retain the speaker's vocal characteristics in the translated speech.[br][br]So, instead of expression-less robotic voice, the translation comes out with the same tone, voice of the original speaker.[br][br]However, the system isn't completely perfect[br][br][br]While Translatotron could be the way to define machine-based speech translation, it is not absolutely perfect.[br][br]Google says the system's translations aren't as accurate as those you get from regular translation technologies.[br][br][br]It still needs to evolve, but in case you want to hear Translatotron speaking, head over to https://bit.ly/2EdKsUb. It is not half bad.[br][br]#Infinix_India... |
|
发表于 2019-05-17 22:13:19
收藏
Like
Stick Card
Jack
