Martin Russell

Progress on phoneme recognition with a continuous-state HMM

2016

Recent advances in automatic speech recognition have used large corpora and powerful computational resources to train complex statistical models from high-dimensional features, to attempt to capture all the variability found in natural speech. Such models …

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 …