IEEE Signal Processing Letters · 2019 · 79 citations · 33 references
Health ProfessionsAudiologyPsychoacousticsQuality ImprovementStatistical LearningSpeech IntelligibilitySpeech Intelligibility EnhancementSpeech RecognitionObjective Function FormulationPerceptual EvaluationQuality Loss FunctionSpeech EnhancementSpeech Enhancement AlgorithmsSpeech Intelligibility MeasurementSpeech Quality AssessmentSpeech Signal Enhancement
Utilizing a human-perception-related objective function to train a speech enhancement model has become a popular topic recently. The main reason is that the conventional mean squared error (MSE) loss cannot represent auditory perception well. One of the typical human-perception-related metrics, which is the perceptual evaluation of speech quality (PESQ), has been proven to provide a high correlation to the quality scores rated by humans. Owing to its complex and non-differentiable properties, however, the PESQ function may not be used to optimize speech enhancement models directly. In this study, we propose optimizing the enhancement model with an approximated PESQ function, which is differentiable and learned from the training data. The experimental results show that the learned surrogate function can guide the enhancement model to further boost the PESQ score (increase of 0.18 points compared to the results trained with MSE loss) and maintain the speech intelligibility.
33
Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever et al. · arXiv (Cornell University) · 2013 · 5.7K citations · Full text
Spectral Normalization for Generative Adversarial Networks
Takeru Miyato, Toshiki Kataoka, Masanori Koyama et al. · arXiv (Cornell University) · 2018 · 2.3K citations · Full text