Cambridge university transcription systems for the multi-genre broadcast challenge

@article{Woodland2015CambridgeUT,
  title={Cambridge university transcription systems for the multi-genre broadcast challenge},
  author={Philip C. Woodland and Xunying Liu and Yanmin Qian and Chao Zhang and Mark J. F. Gales and Panagiota Karanasou and Pierre Lanchantin and Linlin Wang},
  journal={2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
  year={2015},
  pages={639-646}
}
We describe the development of our speech-to-text transcription systems for the 2015 Multi-Genre Broadcast (MGB) challenge. Key features of the systems are: a segmentation system based on deep neural networks (DNNs); the use of HTK 3.5 for building DNN-based hybrid and tandem acoustic models and the use of these models in a joint decoding framework; techniques for adaptation of DNN based acoustic models including parameterised activation function adaptation; alternative acoustic models built… CONTINUE READING
Highly Cited
This paper has 27 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 20 extracted citations

High Order Recurrent Neural Networks for Acoustic Modelling

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018

Improved Tdnns Using Deep Kernels and Frequency Dependent Grid-RNNS

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 3 Excerpts

Phonetic and Graphemic Systems for Multi-genre Broadcast Transcription

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 2 Excerpts

Joint optimisation of tandem systems using Gaussian mixture density neural network discriminative sequence training

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2017

References

Publications referenced by this paper.
Showing 1-10 of 53 references

The MGB challenge: Evaluating multi-genre broadcast media transcription

P. Bell, M.J.F. Gales, +8 authors P. C. Woodland
Proc. ASRU Workshop, Scottsdale, • 2015
View 4 Excerpts
Highly Influenced

Latent Dirichlet Allocation

View 4 Excerpts
Highly Influenced

Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 1 Excerpt

Differentiable pooling for unsupervised speaker adaptation

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 1 Excerpt

Fuse deep neural network and Gaussian mixture model systems”, Automatic Speech Recognition: A Deep Learning Approach, pp. 177–191

D. Yu, L. Deng
2015
View 1 Excerpt

Similar Papers

Loading similar papers…