%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:03:46 PM

@INPROCEEDINGS{Korchagin_HSCMA_2011,
         author = {Korchagin, Danil},
       keywords = {microphone arrays, mobile computing, signal processing, source coding},
       projects = {Idiap, TA2},
          month = may,
          title = {Audio Spatio-Temporal Fingerprints for Cloudless Real-Time Hands-Free Diarization on Mobile Devices},
      booktitle = {Proceedings of the 3rd Joint Workshop on Hands-Free Speech Communication and Microphone Arrays},
           year = {2011},
       location = {Edinburgh, UK},
       crossref = {Korchagin_Idiap-RR-08-2011},
       abstract = {In this paper, we propose a new low bit rate representation of a sound field and a new method for the corresponding cloudless low delay hands-free diarization suitable for low-performance mobile devices, e.g. mobile phones. The proposed audio spatio-temporal fingerprint representation results in low bit rate (500 bytes/second), however contains complete information about continuous audio tracking of multiple acoustic sources in an open, unconstrained environment. The core of the algorithm is based on simultaneous multiple data stream processing using audio spatio-temporal fingerprint representation to cover higher level events relevant for diarization, e.g. turns, interruptions, crosstalk, speech and non-speech segments. Performance levels achieved to date on 5 hours of hand-labelled datasets have shown the feasibility of the approach at the same time as resulting in 7.58\% CPU load on 1-core ultra-low-power mobile processor running at 1 GHz and low algorithmic delay of 112 ms.},
            pdf = {https://publications.idiap.ch/attachments/papers/2011/Korchagin_HSCMA_2011.pdf}
}



crossreferenced publications: 
@TECHREPORT{Korchagin_Idiap-RR-08-2011,
         author = {Korchagin, Danil},
       keywords = {microphone arrays, mobile computing, signal processing, source coding},
       projects = {Idiap, TA2},
          month = {5},
          title = {Audio Spatio-Temporal Fingerprints for Cloudless Real-Time Hands-Free Diarization on Mobile Devices},
           type = {Idiap-RR},
         number = {Idiap-RR-08-2011},
           year = {2011},
    institution = {Idiap},
        address = {Martigny, Switzerland},
       abstract = {In this paper, we propose a new low bit rate representation of a sound field and a new method for the corresponding cloudless low delay hands-free diarization suitable for low-performance mobile devices, e.g. mobile phones. The proposed audio spatio-temporal fingerprint representation results in low bit rate (500 bytes/second), however contains complete information about continuous audio tracking of multiple acoustic sources in an open, unconstrained environment. The core of the algorithm is based on simultaneous multiple data stream processing using audio spatio-temporal fingerprint representation to cover higher level events relevant for diarization, e.g. turns, interruptions, crosstalk, speech and non-speech segments. Performance levels achieved to date on 5 hours of hand-labelled datasets have shown the feasibility of the approach at the same time as resulting in 7.58\% CPU load on 1-core ultra-low-power mobile processor running at 1 GHz and low algorithmic delay of 112 ms.},
            pdf = {https://publications.idiap.ch/attachments/reports/2011/Korchagin_Idiap-RR-08-2011.pdf}
}