Hierarchical bottle neck features for LVCSR

By Christian Plahl, Ralf Schlüter, Hermann Ney. 2010

43 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 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. Li Deng
2. Dong Yu
3. M. Seltzer
4. Brian Kingsbury
5. Mark John Francis Gales
6. Vaibhava Goel
7. Hermann Ney
8. Ralf Schlüter

In Signal Processing

1. Dong Yu
2. Li Deng
3. Jinyu Li
4. Ralf Schlüter
5. Mark John Francis Gales
6. Tara N. Sainath
7. Brian Kingsbury
8. Hermann Ney

Citations in the corpus

• Improved Bottleneck Features Using Pretrained Deep Neural Networks (2011, methodology): “Other features, including multi-resolution variants of RASTA have also been used [11].”
• Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition (2016, background): “Stacked bottleneck networks (SBN) [22, 23, 24] or hierarchical bottleneck networks [25] are a influential acoustic model in hybrid NN/HMM speech recognition.”
• Data augmentation for low resource languages (2014, methodology): “There are numerous configurations possible, such as standard Gaussian mixture model (GMM) based HMM [31], tandem [32], hybrid [33], stacked versions of the tandem [34] and hybrid [33] architectures.”
• Multilingual representations for low resource speech recognition and keyword search (2015, methodology): “These ML features were independently developed at RWTH Aachen (RWTH) [11, 14, 15], Cambridge University (CUED) [16,17] and IBM.”