%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:06:22 PM

@INPROCEEDINGS{Ullmann_ICASSP2015_2015,
         author = {Ullmann, Raphael and Magimai.-Doss, Mathew and Bourlard, Herv{\'{e}}},
       keywords = {Artificial Neural Networks, KL-divergence, Objective intelligibility, phonemes, Speech intelligibility},
       projects = {armasuisse, ScoreL2},
          title = {Objective Speech Intelligibility Assessment through Comparison of Phoneme Class Conditional Probability Sequences},
      booktitle = {40th IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP)},
           year = {2015},
          pages = {4924-4928},
       location = {Brisbane, Australia},
            doi = {10.1109/ICASSP.2015.7178907},
       crossref = {Ullmann_Idiap-RR-16-2014},
       abstract = {Assessment of speech intelligibility is important for the development of speech systems, such as telephony systems and text-to-speech (TTS) systems. Existing approaches to the automatic assessment of intelligibility in telephony typically compare a reference speech signal to a degraded copy, which requires that both signals be from the same speaker.

In this paper, we propose a novel approach that does not have such a requirement, making it possible to also evaluate TTS systems and recent very low bit rate codecs that may modify speaker characteristics.
More specifically, our approach is based on comparing sequences of phoneme class conditional probabilities.

We show the potential of our approach on low bit rate telephony conditions, and compare it against subjective TTS intelligibility scores from the 2011 Blizzard Challenge.},
            pdf = {https://publications.idiap.ch/attachments/papers/2015/Ullmann_ICASSP2015_2015.pdf}
}



crossreferenced publications: 
@TECHREPORT{Ullmann_Idiap-RR-16-2014,
         author = {Ullmann, Raphael and Magimai.-Doss, Mathew and Bourlard, Herv{\'{e}}},
       keywords = {Artificial Neural Networks, KL-divergence, Objective intelligibility, phonemes, Speech intelligibility},
       projects = {armasuisse, ScoreL2},
          month = {10},
          title = {Objective Speech Intelligibility Assessment through Comparison of Phoneme Class Conditional Probability Sequences},
           type = {Idiap-RR},
         number = {Idiap-RR-16-2014},
           year = {2014},
    institution = {Idiap},
       abstract = {Assessment of speech intelligibility is important for the development of speech systems, such as telephony systems and text-to-speech (TTS) systems. Existing approaches to the automatic assessment of intelligibility in telephony typically compare a reference speech signal to a degraded copy, which requires that both signals be from the same speaker. In this paper, we propose a novel approach that does not have such a requirement, making it possible to also evaluate TTS systems and recent very low bit rate codecs that may modify speaker characteristics. More specifically, our approach is based on comparing sequences of phoneme class conditional probabilities. We show the potential of our approach on low bit rate telephony conditions, and compare it against subjective TTS intelligibility scores from the 2011 Blizzard Challenge.},
            pdf = {https://publications.idiap.ch/attachments/reports/2014/Ullmann_Idiap-RR-16-2014.pdf}
}