Investigation on dimensionality reduction of concatenated features with deep neural network for LVCSR systems

By Y. Bao, Hui Jiang, Cong Liu, Yu Hu, Lirong Dai. 2012

25 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, 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 Computer Vision and Pattern Recognition

1. Si Wei
2. Hui Jiang
3. Ossama Abdel-Hamid
4. Shiliang Zhang
5. Lirong Dai
6. Yang Peng
7. Zhenhua Ling
8. Qian Chen

In Media Technology

1. Hui Jiang
2. Ossama Abdel-Hamid
3. Shiliang Zhang

In Signal Processing

1. Hui Jiang
2. Shiliang Zhang
3. Lirong Dai
4. Ossama Abdel-Hamid
5. Si Wei
6. Qingfeng Liu
7. Shaofei Xue
8. Yang Peng

Citations in the corpus

• Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks (2015, background): “For examples, [2, 37, 39, 40] show significant improvements on the worderror rate of speech-to-text transcription task, which was contributed by the effective and”
• Rectified linear neural networks with tied-scalar regularization for LVCSR (2015, methodology): “We follow the same training procedure as described in [17, 18, 19, 20] to train the conventional context dependent DNN/HMM with the tied-triphone state alignment obtained from the above MLE trained GMM/HMMs baseline system.”
• Fast Adaptation of Deep Neural Network Based on Discriminant Codes for Speech Recognition (2014, methodology): “The baseline DNNs are trained as described in [10], [36], [37] with the RBM-based pre-training and the BP-based fine-tuning using the frame-level CE criterion.”