Hermitian Polynomial for Speaker Adaptation of Connectionist Speech Recognition Systems

By Sabato Marco Siniscalchi, Jinyu Li, Chin-Hui Lee. 2013

79 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

1. Jinyu Li
2. Dong Yu
3. Li Deng
4. Florian Metze
5. Chin-Hui Lee
6. Yajie Miao
7. Sabato Marco Siniscalchi
8. S. Renals

In Signal Processing

1. Jinyu Li
2. Dong Yu
3. Li Deng
4. Florian Metze
5. Chin-Hui Lee
6. Yajie Miao
7. S. Renals
8. Sabato Marco Siniscalchi

Citations in the corpus

• Deep Learning: Methods and Applications (2014, methodology): “Finally, the learning architecture developed for bottom-up, detection-based speech recognition proposed in [214] and developed further since 2004, notably in [330, 332, 427] using the DBN–DNN technique, can also be categorized in the discriminative or supervisedlearning deep architecture category.”
• Factorized Hidden Layer Adaptation for Deep Neural Network Based Acoustic Modeling (2016, unknown): “In [49], hidden activation functions are adapted.”
• Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors (2015, background): “In [45], instead of model parameters, the shape of”
• 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”
• A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends (2019, methodology): “6: Autoencoder with 3 neurons in hidden layer recognition [62], computer vision [63] where it is used for the training of higher order factorized Boltzmann machine, speech recognition [75], [76], [77] for pretraining DNN, for pretraining of deep convolutional neural network (CNN) [60], [78], [61].”
• Hierarchical Bayesian combination of plug-in maximum a posteriori decoders in deep neural networks-based speech recognition and speaker adaptation (2017, methodology): “…as testified by the great deal of DNN adaptation techniques available in the recent literature, e.g., (Yu et al., 2013; AbdelHamid and Jiang, 2013; Saon et al., 2013; Siniscalchi et al., 2013; Li et al., 2014; Remes et al., 2015; Huang et al., 2015a; Swietojanski et al., 2016; Huang et al., 2017).”
• Fast Adaptation of Deep Neural Network Based on Discriminant Codes for Speech Recognition (2014, methodology): “In [16], Hermitian-based MLP (HB-MLP) method achieves the adaptive capability through the use of new orthonormal Hermite polynomials as activation functions in NN.”
• Rapid adaptation for deep neural networks through multi-task learning (2015, background): “In recent years, several adaptation approaches have been proposed to address this mismatch issue, such as regularization based [3, 4], subspace based [5, 6], transformation based [7, 8, 9, 10], i-Vector based [11], native neural network adaptation [12, 13, 14], factorized adaptation [15] and speaker”
• Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models (2014, background): “Smaller subsets of the DNN weights may be modified, including adaptation of output layer biases [20], and adaptation of the bias and slope of hidden units (a contrast experiment in [29]).”
• Feature space maximum a posteriori linear regression for adaptation of deep neural networks (2014, methodology): “…network (ANN) [16] HMM hybrid, known as connectionist systems [17] in which the CD-DNN-HMM is a special case, there are also many adaptation attempts, such as transformation-based [18, 19, 20, 21], conservative-based [22, 23, 24], subspace-based [25] and activation function based [26] approaches.”