Comparing multilayer perceptron to Deep Belief Network Tandem features for robust ASR

By Oriol Vinyals, Suman V. Ravuri. 2011

64 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

Deep Learning: Methods and Applications (2014, methodology): “Vinyals and Ravuri [379] investigated the tandem approaches to noise-robust speech recognition, where DNNs were trained directly with noisy speech to generate posterior features.”
Krylov Subspace Descent for Deep Learning (2011, background): “Further details on the setup can be found in [14].”
Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition (2018, background): “Alternatively, robustness can also be achieved by training using features that are domain invariant [10, 11, 12, 13, 14].”
An investigation of deep neural networks for noise robust speech recognition (2013, unknown): “[13, 14] and feature enhancement methods that use stereo data to train a network to map from noisy to clean features, e.”
Word-level Acoustic Modeling with Convolutional Vector Regression (2012, background): “Recent work has shown substantial improvements to such systems are possible by using deep neural networks to model the acoustic signal (Dahl et al., 2011; Mohamed et al., 2011; Vinyals & Ravuri, 2011).”
Revisiting Recurrent Neural Networks for robust ASR (2012, methodology): “The first two columns correspond to the reported PER in [2].”
Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition (2014, background): “Index Terms— robust speech recognition, feature denoising, denoising autoencoder, deep neural network”