Application of Pretrained Deep Neural Networks to Large Vocabulary Conversational Speech Recognition

34 citations recorded by the source corpus.

How researchers see this paper

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

Improving neural networks by preventing co-adaptation of feature detectors (2012, methodology): “Recently, deep, pre-trained, feedforward neural networks that map a short sequence of frames into a probability distribution over HMM states have been shown to outperform traditional Gaussian mixture models on both TIMIT [12] and a variety of more realistic large vocabulary tasks [6, 10].”
Feature Learning in Deep Neural Networks - A Study on Speech Recognition Tasks (2013, methodology): “Because the temporal structure of the HMM is maintained, we refer to these models as CD-DNN-HMM acoustic models.”
The Deep Tensor Neural Network With Applications to Large Vocabulary Speech Recognition (2013, methodology): “Subsequent work on Google voice search and YouTube data [7] and on Broadcast News [8], [9] confirmed the effectiveness of the CD-DNN-HMMs for large vocabulary speech recognition.”
Deep Neural Networks for Acoustic Modeling in Speech Recognition (2012, methodology): “[47] used this model to obtain approximately 5,870 hours of a ligned training data for a DBN-DNN acoustic model that predicts the 7,969 HMM state posteriors fr m the acoustic input.”
Context-dependent deep neural networks for commercial Mandarin speech recognition applications (2013, methodology): “Especially, Google voice input recognition task used about 5870 hours of training data and achieved 23% relative word error reduction compared to the best GMM-based system for this task [12][13].”