问题:

Good evening, I'm working on a project with Kinect and I need to perform a gender-recognition using the voice information caught by the microphone of the sensor. The recognition could also be text-based, i.e. the sentence said by the user could always be the same. I "just" need the binary answer male/female.

I've checked the quite popular open-source Sphinx but I can't understand if it could be used for my needs.

Any idea of what I could use?
Thanks in advance.

回答1:

For sake of completeness, finally I solved the recognition task without analyzing the voice input.

Gender can be detected with an acceptable precision also by learning and then classifying visual biometric traits. I used speech recognition only as "interface" to activate the demo.

回答2:

There are several ways to achieve this. You can track pitch (lower pitch values will be male, otherwise female). Or try to build a GMM (Sphinx cannot do this, but HTK can), with one model for male, other for female and another to children.