I'm planning on developing a speech recognition mobile app --- one that checks whether you've mispronounced a word and of course, would point out its correct pronunciation. To be honest, I'm a newbie at this and I would like to ask for which topics should I check and which tutorials (if any) could I watch to get a more in-depth knowledge about this.
The software will, of course, include the recording of the audio, but what really bothers me is how this recorded audio of the user's pronunciation be compared with the correct/standard pronunciation.
Thank you in advance for any reply :)