Sequence classification using the high-level features extracted from deep neural networks

By Li Deng, Jianshu Chen. 2014

51 citations recorded by the source corpus.

The recent success of deep neural networks (DNNs) in speech recognition can be attributed largely to their ability to extract a specific form of high-level features from raw acoustic data for subsequent sequence classification or recognition tasks. Among the many possible forms of DNN features, what forms are more useful than others and how effective these DNN features are in connection with the different types of downstream sequence recognizers remained unexplored and are the focus of this paper. We report our recent work on the construction of a diverse set of DNN features, including the vectors extracted from the output layer and from various hidden layers in the DNN. We then apply these features as the inputs to four types of classifiers to carry out the identical sequence classification task of phone recognition. The experimental results show that the features derived from the top hidden layer of the DNN perform the best for all four classifiers, especially for the autoregressive-moving-average (ARMA) version of a recurrent neural network. The feature vector derived from the DNN's output layer performs slightly worse but better than any of the hidden layers in the DNN except the top one.

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

1. Li Deng
2. Dong Yu
3. Jinyu Li
4. Yoshua Bengio
5. Xiaodong He
6. Jianfeng Gao
7. Frank Torsten Bernd Seide
8. Yifan Gong

In Signal Processing

1. Li Deng
2. Dong Yu
3. Jinyu Li
4. Yifan Gong
5. Frank Torsten Bernd Seide
6. Yoshua Bengio
7. S. Renals
8. M. Seltzer

Citations in the corpus

• Deep Learning: Methods and Applications (2014, methodology): “More recently, a recurrent neural network (RNN) is used as the “backend” recognizer receiving the high-dimensional, DNN-derived features as the input without dimensionality reduction [48, 85].”
• Phone recognition with hierarchical convolutional deep maxout networks (2015, unknown): “DNN + RNN [49] 18.”
• Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition (2014, unknown): “Literature [23] reported that a better phoneme recognition perfo rmance could be achieved by applying this strategy for RNNs, althou gh they”