ملف الباحث
Stephen Houghton
ورقة واحدة في مجموعة PaperMetrix
المنشورات
أوراق هذا المؤلف
-
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 …