Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.
Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
I currently have a mobile application that can record speech as either a WAV or MP3 and would like to convert it to text. I have looked around – Microsoft Speech, UCMA, etc — but haven’t seen any good examples of how to do it. Can someone help out here?
FYI – We have access to MS Lync.
Look forward to any responses,
James
There’s a sample of using the UCMA 3.0 SDK to perform speech recognition, available here. However, from experience (and I’ve love to be proved wrong here) you can only recognise a specific response from a pre-determined set of options. So, you can ask “How was your day” and tell UCMA that valid responses are “Good”, “Fair”, “Bad” and it will then attempt to match any of those. I’ve not seen it be able to ‘just’ do free-speech conversion. (a much harder problem)
This might be something the Microsoft Speech API can do better. Try this post for a head start.