Skype has invited its users to try a “Preview” version of their Translator product and provide feedback. The program is available for face-to-face, real-time audio/video conversations in four languages so far: English, Spanish, Mandarin and Italian, with more on the way. Instant Messaging (IM) is available in over 45 languages, from Dutch to Hindi to Klingon.
Developed by Microsoft, Skype Translator requires Windows 8 and up, and its translation quality has been compared to that of Babel Fish and Google Translate. Skype’s blog states that they have been “investing in speech recognition, automatic translation and machine learning technologies for more than a decade.”
Nearly as important as the Bing Translator algorithm Skype Translator relies on, is the voice recognition component that initiates and completes the transformation of a speaker’s words into something in the target language that is understandable on the other end. The Translator first turns spoken words to text, then uses machine learning to interpret the grammar, and statistical matching within a text database to pin down meanings. That “written” translation is then funneled back through voice recognition software and “Jane” or “Bob” – the female and male Skype AI (Artificial Intelligence) voices – deliver what Skype hopes to be a pleasant, human-like audio expression of the speaker’s meaning.
Microsoft’s research into deep “artificial neural networks” (ANNs) in the early 2000’s led to the AI that makes all of this possible. ANNs are sets of statistical learning algorithms that create a responsiveness to input that resembles the experienced-based development of the human mind, thus enabling “understanding” of complex systems such as language. It was this work that led to what Wired Magazine calls “Skype’s most startling breakthrough: the ability to reliably recognize almost anybody’s speech,” including the interpretation of rhythm and intonation.
There is also a more controversial issue that Skype and Microsoft have made some preliminary choices about: certain elements are “scrubbed” from translations, that is, they are not acknowledged or translated at all. Repetitive speech tics and profanity, for example. Therefore, in essence Skype Translator currently does a bit of conversation editing, which could feel like censoring. This will undoubtedly become one of the areas that Skype Translator users will give feedback about over time as they utilize the program to personalize their global communication.