Hidden Markov models (HMMs) and Gaussian mixture models (GMMs) are the two most common types of acoustic models used in statistical parametric approaches for generating …
L Deng, D Yu - Foundations and trends® in signal processing, 2014 - nowpublishers.com
This monograph provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks. The application areas …
It has been previously shown that, when both acoustic and articulatory training data are available, it is possible to improve phonetic recognition accuracy by learning acoustic …
ZH Ling, L Deng, D Yu - IEEE transactions on audio, speech …, 2013 - ieeexplore.ieee.org
This paper presents a new spectral modeling method for statistical parametric speech synthesis. In the conventional methods, high-level spectral parameters, such as mel-cepstra …
Studies have shown that articulatory information helps model speech variability and, consequently, improves speech recognition performance. But learning speaker-invariant …
Estimating articulatory movements from speech acoustic features is known as acoustic-to- articulatory inversion (AAI). Large amount of parallel data from speech and articulatory …
ZH Ling, L Deng, D Yu - 2013 IEEE International Conference …, 2013 - ieeexplore.ieee.org
This paper presents a new spectral modeling method for statistical parametric speech synthesis. In contrast to the conventional methods in which high-level spectral parameters …
This paper presents a deep neural network (DNN) to extract articulatory information from the speech signal and explores different ways to use such information in a continuous speech …
Hybrid deep neural network–hidden Markov model (DNN-HMM) systems have become the state-of-the-art in automatic speech recognition. In this paper we experiment with DNN-HMM …