Hello,
I would like to ask you If it is possible to get/recommend some online sources about the background of used synthesis in Bing Translator (speak method in API).
I'm writting a paper and I am looking for information about it. I have found API documentation and similar sources. but I would be really interested in the background, especially which type of the synthesis do you use and so on. I guess it could be frequency synthesis but I suppose it would not be so simple. So I suppose a usage of neural networks, Hidden Markov Model and similar models.
I really understand that it is your know-how but I suppose there must be some basic information about the background of the technology.
Thanks.