Deep and Wide: Multiple Layers in Automatic Speech Recognition

By Nelson Morgan. 2012

156 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

In Signal Processing

Citations in the corpus

Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition (2017, background): “The recent success of a neural network based architecture mainly comes from its deep architecture [15, 16].”
Deep Learning: Methods and Applications (2014, methodology): “Note the use of “hybrid” in (3) above is different from that used sometimes in the literature, which refers to the hybrid systems for speech recognition feeding the output probabilities of a neural network into an HMM [17, 25, 42, 261].”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, methodology): “The recent article of [33] gives an excellent review on othermajor existing discriminativemodels in speech recognition based mainly on the traditional neural network or MLP architecture using backpropagation learning with random initialization.”
Deep bottleneck features for i-vector based text-independent speaker verification (2015, methodology): “The tandem approach is the most common approach in extracting features from a DNN [19].”
Building DNN acoustic models for large vocabulary speech recognition (2014, background): “Neural networks with only a single hidden layer perform worse than their deeper counterparts on a variety of speech tasks, even when the total number of model parameters is held fixed [21], [20], [26].”
New types of deep neural network learning for speech recognition and related applications: an overview (2013, background): “multi-layer neural networks; see a comprehensive review in [24] and reviews of earlier work in [6][44].”
A survey of deep neural network architectures and their applications (2017, background): “them, HMMs and GMMs are widely used for acoustic modeling to g enerate low-level acoustic contents from highlevel acoustic inputs [32], [34], [79], [101], [116], [120] , [130].”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, background): “Examples include deep-structured CRF, tandem-MLP architecture [94], [258], deep convex or stacking network [248] and its tensor version [242], [243], [259], and detection-based ASR architecture [235], [236], [260].”
State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems (2017, background): “It is worth noting that the hybrid deep architecture is not the same as feeding the outputs of a traditional neural network to a Hidden Markov Model (HMM) [24]–[26].”
Speech Emotion Recognition Using Deep Learning Techniques: A Review (2019, methodology): “A DNN based on Generalized Discriminant Analysis (GerDA) for SER is proposed in [26], [125], [127].”
Deep Neural Networks for Acoustic Modeling in Speech Recognition (2012, methodology): “For a summary of such methods, commonly known as the tandem approach, see [60], [61].”
Speech Recognition Using Deep Neural Networks: A Systematic Review (2019, background): “For instance, Morgan [9] conducted a review in the area of speech recognition assisted with discriminatively trained feed-forward networks.”
Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature (2015, methodology): “The former is called the hybrid approach [9][16][17] and the latter is called the TANDEM approach [18][19][20].”
A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion (2013, background): “(For recent reviews on the use of neural networks in speech recognition, see [29][17]).”