%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:00:34 PM

@INPROCEEDINGS{Muckenhirn_ICASSP_2018,
         author = {Muckenhirn, Hannah and Magimai.-Doss, Mathew and Marcel, S{\'{e}}bastien},
       keywords = {Convolutional neural network, End-to-end learning, Fundamental frequency, recognition, speaker verification},
       projects = {Idiap, UNITS},
          month = apr,
          title = {Towards directly modeling raw speech signal for speaker verification using CNNs},
      booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
           year = {2018},
          pages = {4884-4888},
       location = {Calgary, CANADA},
           isbn = {978-1-5386-4658-8},
       crossref = {Muckenhirn_Idiap-RR-30-2017},
       abstract = {Speaker verification systems traditionally extract and model cepstral features or filter bank energies from the speech signal. In this paper, inspired by the success of neural network-based approaches to model directly raw speech signal for applications such as speech recognition, emotion recognition and anti-spoofing, we propose a speaker verification approach where speaker discriminative information is directly learned from the speech signal by: (a) first training a CNN-based speaker identification system that takes as input raw speech signal and learns to classify on speakers (unknown to the speaker verification system); and then (b) building a speaker detector for each speaker in the speaker verification system by replacing the output layer of the speaker identification system by two outputs (genuine, impostor), and adapting the system in a discriminative manner with enrollment speech of the speaker and impostor speech data. Our investigations on the Voxforge database shows that this approach can yield systems competitive to state-of-the-art systems. An analysis of the filters in the first convolution layer shows that the filters give emphasis to information in low frequency regions (below 1000 Hz) and implicitly learn to model fundamental frequency information in the speech signal for speaker discrimination.},
            pdf = {https://publications.idiap.ch/attachments/papers/2018/Muckenhirn_ICASSP_2018.pdf}
}



crossreferenced publications: 
@TECHREPORT{Muckenhirn_Idiap-RR-30-2017,
         author = {Muckenhirn, Hannah and Magimai.-Doss, Mathew and Marcel, S{\'{e}}bastien},
       projects = {Idiap, UNITS},
          month = {11},
          title = {Towards directly modeling raw speech signal for speaker verification using CNNs},
           type = {Idiap-RR},
         number = {Idiap-RR-30-2017},
           year = {2017},
    institution = {Idiap},
            pdf = {https://publications.idiap.ch/attachments/reports/2017/Muckenhirn_Idiap-RR-30-2017.pdf}
}