CONF Ullmann_ICASSP2015_2015/IDIAP Objective Speech Intelligibility Assessment through Comparison of Phoneme Class Conditional Probability Sequences Ullmann, Raphael Magimai-Doss, Mathew Bourlard, Hervé Artificial Neural Networks KL-divergence Objective intelligibility phonemes Speech intelligibility EXTERNAL https://publications.idiap.ch/attachments/papers/2015/Ullmann_ICASSP2015_2015.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Ullmann_Idiap-RR-16-2014 Related documents 40th IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP) Brisbane, Australia 2015 4924-4928 10.1109/ICASSP.2015.7178907 doi 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. REPORT Ullmann_Idiap-RR-16-2014/IDIAP Objective Speech Intelligibility Assessment through Comparison of Phoneme Class Conditional Probability Sequences Ullmann, Raphael Magimai-Doss, Mathew Bourlard, Hervé Artificial Neural Networks KL-divergence Objective intelligibility phonemes Speech intelligibility EXTERNAL https://publications.idiap.ch/attachments/reports/2014/Ullmann_Idiap-RR-16-2014.pdf PUBLIC Idiap-RR-16-2014 2014 Idiap October 2014 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.