Recurrent Poisson Process Unit for Speech Recognition

@inproceedings{Huang2019RecurrentPP,
  title={Recurrent Poisson Process Unit for Speech Recognition},
  author={Hengguang Huang and Hao Wang and B. Mak},
  booktitle={AAAI},
  year={2019}
}
Over the past few years, there has been a resurgence of interest in using recurrent neural network-hidden Markov model (RNN-HMM) for automatic speech recognition (ASR). Some modern recurrent network models, such as long shortterm memory (LSTM) and simple recurrent unit (SRU), have demonstrated promising results on this task. Recently, several scientific perspectives in the fields of neuroethology and speech production suggest that human speech signals may be represented in discrete point… Expand
Deep Graph Random Process for Relational-Thinking-Based Speech Recognition
Fully Neural Network based Model for General Temporal Point Processes
Spatio-temporal SRU with global context-aware attention for 3D human action recognition
Learning Temporal Point Processes with Intermittent Observations
Intensity-Free Learning of Temporal Point Processes
Universal Approximation with Neural Intensity Point Processes
Scalable and Interpretable Marked Point Processes
A Survey on Bayesian Deep Learning

References

SHOWING 1-10 OF 37 REFERENCES
Speech recognition with deep recurrent neural networks
Hybrid speech recognition with Deep Bidirectional LSTM
Distinct triphone acoustic modeling using deep neural networks
Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
Point process models for event-based speech recognition
Recent progresses in deep learning based acoustic models
  • Dong Yu, Jinyu Li
  • Computer Science, Engineering
  • IEEE/CAA Journal of Automatica Sinica
  • 2017
Quasi-Recurrent Neural Networks
Maximum likelihood linear transformations for HMM-based speech recognition
  • M. Gales
  • Computer Science
  • Comput. Speech Lang.
  • 1998
The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process
Toward a model for lexical access based on acoustic landmarks and distinctive features.
  • K. Stevens
  • Computer Science, Medicine
  • The Journal of the Acoustical Society of America
  • 2002
...
1
2
3
4
...