Acoustic Modeling With Hierarchical Reservoirs

79 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning: Methods and Applications (2014, methodology): “[365] applied such models to phone recognition, with reasonably good accuracy obtained.”
Porting concepts from DNNs back to GMMs (2013, methodology): “Given that deep systems can learn phonotactic constraints by itself when being fed with a large window of frames [4, 27] while HMM+GMM systems commend a more strict separation between acoustics modeling (GMMs) and phonotactics (phone N-gram), we compare the systems over a range of phone Ngrams.”
Randomness in neural networks: an overview (2017, background): “Triefenbach et al.(84) investigated this idea for acoustic modeling in which every layer of the network is trained to distinguish between acoustic entities of increasing temporal duration.”