%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 11:37:05 AM

@ARTICLE{Parthasarathi_TASLP_2012,
         author = {Parthasarathi, Sree Hari Krishnan and Bourlard, Herv{\'{e}} and Gatica-Perez, Daniel},
       projects = {Idiap, FP 7, SNSF-MULTI},
          title = {Wordless Sounds: Robust Speaker Diarization using Privacy-Preserving Audio Representations},
        journal = {IEEE Transactions on Audio, Speech, and Language Processing},
           year = {2012},
       crossref = {Parthasarathi_Idiap-RR-28-2012},
       abstract = {This paper investigates robust privacy-sensitive audio features for speaker diarization in multiparty conversations: ie., a set of audio features having low linguistic information for speaker diarization in a single and multiple distant microphone scenarios. We systematically investigate Linear Prediction (LP) residual. Issues such as prediction order and choice of representation of LP residual are studied. Additionally, we explore the combination of LP residual with subband information from 2.5 kHz to 3.5 kHz and spectral slope. Next, we propose a supervised framework using deep neural architecture for deriving privacy-sensitive audio features. We benchmark these approaches against the traditional Mel Frequency Cepstral Coefficients (MFCC) features for speaker diarization in both the microphone scenarios. Experiments on the RT07 evaluation dataset show that the proposed approaches yield diarization performance close to the MFCC features on the single distant microphone dataset. To objectively evaluate the notion of privacy in terms of linguistic information, we perform human and automatic speech recognition tests, showing that the proposed approaches to privacy-sensitive audio features yield much lower recognition accuracies compared to MFCC features.},
            pdf = {https://publications.idiap.ch/attachments/papers/2012/Parthasarathi_TASLP_2012.pdf}
}



crossreferenced publications: 
@TECHREPORT{Parthasarathi_Idiap-RR-28-2012,
         author = {Parthasarathi, Sree Hari Krishnan and Bourlard, Herv{\'{e}} and Gatica-Perez, Daniel},
       projects = {Idiap, FP 7, SNSF-MULTI},
          month = {9},
          title = {Wordless Sounds: Robust Speaker Diarization using Privacy-Preserving Audio Representations},
           type = {Idiap-RR},
         number = {Idiap-RR-28-2012},
           year = {2012},
    institution = {Idiap},
       abstract = {This paper investigates robust privacy-sensitive audio features for speaker diarization in multiparty conversations: ie., a set of audio features having low linguistic information for speaker diarization in a single and multiple distant microphone scenarios. We systematically investigate Linear Prediction (LP) residual. Issues such as prediction order and choice of representation of LP residual are studied. Additionally, we explore the combination of LP residual with subband information from 2.5 kHz to 3.5 kHz and spectral slope. Next, we propose a supervised framework using deep neural architecture for deriving privacy-sensitive audio features. We benchmark these approaches against the traditional Mel Frequency Cepstral Coefficients (MFCC) features for speaker diarization in both the microphone scenarios. Experiments on the RT07 evaluation dataset show that the proposed approaches yield diarization performance close to the MFCC features on the single distant microphone dataset. To objectively evaluate the notion of privacy in terms of linguistic information, we perform human and automatic speech recognition tests, showing that the proposed approaches to privacy-sensitive audio features yield much lower recognition accuracies compared to MFCC features.},
            pdf = {https://publications.idiap.ch/attachments/reports/2011/Parthasarathi_Idiap-RR-28-2012.pdf}
}