Speech Processing

Hi,

You can do general data mining on audio data. Our CEO Ingo did this in some thesis. But that was more destinguishing between different music styles.

Do you really want to have Speech to Text?

Best,
Martin

I want to extract features and process the signals.

Thanks

To get what? A classification about the sentiment or the spoken text in a written form?

The first one might be possible, the later one not that i know of.

It is okay if i can show me how to get feature extraction (MFCC or LPC).

Thanks

I don't have a direct link. I know that our CEO Ingo did this for his Diploma thesis.

There are some papers around like this: http://sfb876.tu-dortmund.de/PublicPublicationFiles/mierswa_morik_2005a.pdf and this was one of the first projects done with RM (back then named Yale). So i would really think that those options are still available.
However, i never did this myself, so i don't know which operators to use excactly.

Hello

Some of the operators used in the paper are not available any more.

There is some history referred to here... http://rapid-i.com/rapidforum/index.php/topic,1608.msg6275.html#msg6275

regards

Andrew

You can do general data mining on audio data. Our CEO Ingo did this in some thesis. But that was more destinguishing between different music styles.https://pmkisanyojanastatus.com/