logo Idiap Research Institute        
 [BibTeX] [Marc21]
LP Residual Features for Robust, Privacy-Sensitive Speaker Diarization
Type of publication: Idiap-RR
Citation: Parthasarathi_Idiap-RR-14-2011
Number: Idiap-RR-14-2011
Year: 2011
Month: 5
Institution: Idiap
Abstract: 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.
Projects Idiap
Authors Parthasarathi, Sree Hari Krishnan
Bourlard, Hervé
Gatica-Perez, Daniel
Added by: [ADM]
Total mark: 0
  • Parthasarathi_Idiap-RR-14-2011.pdf (MD5: eb78f44c85e4191fc1be9c18bd4d0373)