ملف الباحث

Stephen Houghton

ورقة واحدة في مجموعة PaperMetrix

المنشورات

أوراق هذا المؤلف

  1. Interpretation of Low Dimensional Neural Network Bottleneck Features in Terms of Human Perception and Production

    2016

    Low-dimensional ‘bottleneck’ features extracted from neural networks have been shown to give phoneme recognition accuracy similar to that obtained with higher-dimensional MFCCs, using GMM-HMM models. Such features have also been shown to preserve well the …