Hi, I’m just started to develop a speech recognition system. I already collected the audio to be processed. Originally the speech signal is in analog. My concern here is can Audacity convert analog speech signal to digital speech signal? So that it can be preprocess. If can, how? Thank you!
How have you done that? Do you have the collection on your computer?
What is your level of experience as a software developer?
Yes, I have the audio data in .wav format in my laptop and I’m a student actually, currently doing a research in Speech Recognition System.
As you can read on Wikipedia (WAV - Wikipedia) WAV files are digital.
Windows has speech-recognition built-in …
https://wikipedia.org/wiki/Windows_Speech_Recognition
Thank you so much Steve and Trebor.
Oh I see. So I can skip the A/D Conversion process right? I can went straight away to the next process of preprocessing speech signal which is noise removal then pre-emphasis and lastly framing and windowing?
Or is it framing and windowing considered as a same step? And can I accomplish this tasks with Audacity?
Thank you.