Feature learning in deep neural networks-studies on speech recognition tasks
Recent studies have shown that deep neural networks (DNNs) perform significantly better
than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech …
than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech …
Building DNN acoustic models for large vocabulary speech recognition
Understanding architectural choices for deep neural networks (DNNs) is crucial to improving
state-of-the-art speech recognition systems. We investigate which aspects of DNN acoustic …
state-of-the-art speech recognition systems. We investigate which aspects of DNN acoustic …
[PDF][PDF] Exploring convolutional neural network structures and optimization techniques for speech recognition.
Recently, convolutional neural networks (CNNs) have been shown to outperform the
standard fully connected deep neural networks within the hybrid deep neural …
standard fully connected deep neural networks within the hybrid deep neural …
Convolutional neural networks for speech recognition
Recently, the hybrid deep neural network (DNN)-hidden Markov model (HMM) has been
shown to significantly improve speech recognition performance over the conventional …
shown to significantly improve speech recognition performance over the conventional …
Deep learning: from speech recognition to language and multimodal processing
L Deng - APSIPA Transactions on Signal and Information …, 2016 - cambridge.org
While artificial neural networks have been in existence for over half a century, it was not until
year 2010 that they had made a significant impact on speech recognition with a deep form of …
year 2010 that they had made a significant impact on speech recognition with a deep form of …
Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMs in acoustic modeling
J Pan, C Liu, Z Wang, Y Hu… - 2012 8th International …, 2012 - ieeexplore.ieee.org
Recently, it has been reported that context-dependent deep neural network (DNN) has
achieved some unprecedented gains in many challenging ASR tasks, including the well …
achieved some unprecedented gains in many challenging ASR tasks, including the well …
[PDF][PDF] Deep convex net: A scalable architecture for speech pattern classification
We recently developed context-dependent DNN-HMM (Deep-Neural-Net/Hidden-Markov-
Model) for large-vocabulary speech recognition. While achieving impressive recognition …
Model) for large-vocabulary speech recognition. While achieving impressive recognition …
Noisy training for deep neural networks in speech recognition
Deep neural networks (DNNs) have gained remarkable success in speech recognition,
partially attributed to the flexibility of DNN models in learning complex patterns of speech …
partially attributed to the flexibility of DNN models in learning complex patterns of speech …
[PDF][PDF] Distilling knowledge from ensembles of neural networks for speech recognition.
Y Chebotar, A Waters - Interspeech, 2016 - isca-archive.org
Speech recognition systems that combine multiple types of acoustic models have been
shown to outperform single-model systems. However, such systems can be complex to …
shown to outperform single-model systems. However, such systems can be complex to …
Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
We propose a novel context-dependent (CD) model for large-vocabulary speech recognition
(LVSR) that leverages recent advances in using deep belief networks for phone recognition …
(LVSR) that leverages recent advances in using deep belief networks for phone recognition …