Hierarchical neural net architectures for feature extraction in ASR
نویسندگان
چکیده
This paper presents the use of neural net hierarchy for feature extraction in ASR. The recently proposed Bottle-Neck feature extraction is extended and used in hierarchical structures to enhance the discriminative property of the features. Although many ways of hierarchical classification/feature extraction have been proposed, we restricted ourselves to use the outputs of the first stage neural network together with its inputs. This approach is evaluated on meeting speech recognition using RT’05 and RT’07 test sets. The evaluated hierarchical feature extraction brings consistent improvement over the use of just the first level neural net.
منابع مشابه
Why do ASR Systems Despite Neural Nets Still Depend on Robust Features
To which extent can neural nets learn traditional signal processing stages of current robust ASR front-ends? Will neural nets replace the classical, often auditory-inspired feature extraction in the near future? To answer these questions, a DNN-based ASR system was trained and tested on the Aurora4 robust ASR task using various (intermediate) processing stages. Additionally, the training set wa...
متن کامل(Deep) Neural Networks
This work continues in development of the recently proposed Bottle-Neck features for ASR. A five-layers MLP used in bottleneck feature extraction allows to obtai arbitrary feature size without dimensionality reduction by transforms, independently on the MLP training targets. The MLP topology – number and sizes of layers, suitable training targets, the impact of output feature transforms, the ne...
متن کاملGAN-Assisted Two-Stream Neural Network for High-Resolution Remote Sensing Image Classification
Using deep learning to improve the capabilities of high-resolution satellite images has emerged recently as an important topic in automatic classification. Deep networks track hierarchical high-level features to identify objects; however, enhancing the classification accuracy from low-level features is often disregarded. We therefore proposed a two-stream deep-learning neural network strategy, ...
متن کاملClassification of Idiopathic Interstitial Pneumonia CT Images using Convolutional-net with Sparse Feature Extractors
We propose a computer aided diagnosis (CAD) system for classification of idiopathic interstitial pneumonias (IIPs). High resolution computed tomography (HRCT) images are considered as effective for diagnosis of IIPs. Our proposed CAD system is based on the convolutionalnet that is bio-plausible neural network model inspired from the visual system such like human. The convolutional-net extract l...
متن کاملAlgorithms- a Review
Speech recognition basically means talking to a computer, having it recognize what Speakers are saying. The person would also like to interact with computer via speech. It can be accomplished by speech recognition system in which computer identifies the word spoken by a speaker into a microphone. Speech recognition is becoming more complex and a challenging task. The research is focusing on lar...
متن کامل