Convolutional deep maxout networks for phone recognition

By László Tóth. 2014

44 citations recorded by the source corpus.

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. Jianfei Cai
2. Lorenzo Rosasco
3. Jiuxiang Gu
4. Tomaso A. Poggio
5. Chiyuan Zhang
6. Amir Shahroudy
7. Georgios Evangelopoulos
8. Leonardo Badino

In Signal Processing

1. Chiyuan Zhang
2. Tomaso A. Poggio
3. Jianfei Cai
4. Lorenzo Rosasco
5. Georgios Evangelopoulos
6. Leonardo Badino
7. Gang Wang
8. Jiuxiang Gu

Citations in the corpus

• Recent advances in convolutional neural networks (2015, background): “Recently, very deep CNNs have shown impressive performance in ASR [294, 295].”
• Phonetic Context Embeddings for DNN-HMM Phone Recognition (2016, methodology): “, [8, 24]) the acoustic coefficient vectors used as input to the DNN consisted of 40 log melfiltered spectral coefficients (MFSCs) plus deltas and deltadeltas, and log energy plus its derivatives, all computed every 10ms from 25ms long frames .”
• Discriminative template learning in group-convolutional networks for invariant speech representations (2015, methodology): “…convolutional networks [18], that redefine weight-sharing for robustness to 2D rotations and scal- Copyright © 2015 ISCA September 6-10, 2015, Dresden, Germany 3229 10 .2 14 37 /I nt er sp ee ch .2 01 5- 65 0 ing, and scattering networks defined using wavelets over rototranslation groups [19].”