LP Residual Features for Robust, Privacy-Sensitive Speaker Diarization

We present a comprehensive study of linear prediction residual for speaker diarization on single and multiple distant microphone conditions in privacy-sensitive settings, a requirement to analyze a wide range of spontaneous conversations. Two representations of the residual are compared, namely real-cepstrum and MFCC, with the latter performing better. Experiments on RT06eval show that residual with subband information from 2.5 kHz to 3.5 kHz and spectral slope yields a performance close to traditional MFCC features. As a way to objectively evaluate privacy in terms of linguistic information, we perform phoneme recognition. Residual features yield low phoneme accuracies compared to traditional MFCC features.


Year:
2011
Publisher:
Idiap
Laboratories:




 Record created 2011-07-06, last modified 2018-03-17

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)