FACTORIZED DEEP NEURAL NETWORKS FOR ADAPTIVE SPEECH RECOGNITION

By Dong Yu, Xin Chen, Li Deng. 2012

29 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.

Citations in the corpus

Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code (2013, methodology): “In [20], hidden factors are used in the top layer to represent speaker and environment in a factorial NN model.”
The Deep Tensor Neural Network With Applications to Large Vocabulary Speech Recognition (2013, methodology): “In Table III we also included the results achieved with the joint factorized DNN (JFDNN) described in [21].”
KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition (2013, methodology): “In [26] a speaker subspace and a speech subspace are estimated and combined using tensors.”
Factorized Hidden Layer Adaptation for Deep Neural Network Based Acoustic Modeling (2016, methodology): “In factorized DNN [59], tensors are used to connect different factors of variability.”
Large Vocabulary Speech Recognition Using Deep Tensor Neural Networks (2012, background): “Hutchinson, Deng and Yu [13] replaced the single sigmoid hidden layer with a tensor layer in the stacking networks.”
Maximum a posteriori adaptation of network parameters in deep models (2015, background): “Recent approaches, such as regularization based [7, 8], subspace based [9, 10], transformation based [6, 11, 12, 13], i-Vector based [14], native neural network based [15, 16, 17], factorization based [18] and fast adaptation schemes based on discriminant speaker codes [19, 16, 20, 21], have been pr”