I want to classify audio advertisements based on user preferences.So I need to extract features from the audio files which will be pertaining to users.thus I need a way to extract features.I want to know whether there is a method for this without processing the text form of this audio.
Hi Tharindra
I don't think there are any short cuts to extracting qualitative data from audio files. As a qualitative researcher I always go down the transcribe verbatim route, which is the most time consuming part of qualitative data analysis. You could always pay for a transcription service, or do it your self. The good thing about doing it yourself is that it really helps you to familiarise your self with the data that you have.
Once you have the transcribed data you are then in a position to employ any of the qualitative data analysis techniques that you are comfortable using.
Hope this helps
Martyn
Hi Tharindra,
Maybe it would be worth for you to check PRAAT, a software for phonetic science.
http://www.fon.hum.uva.nl/praat/
Another possible software package for qualitative analysis is Ninvo. Lots of information about this on the net.
Thank you everyone for your instant response. Your solutions are highly appreciated.
- Badges
- Science topic
- Similar topics
- Psychology