Noise Robustness Automatic Speech Recognition with Convolutional Neural Network and Time Delay Neural Network

Wang J, Wang D, Chen Y, Lu X, Zheng C. Noise Robustness Automatic Speech Recognition with Convolutional Neural Network and Time Delay Neural Network. In: AES Convention 147. Audio Engineering Society; 2019. Paper 10272. Available from: https://aes.org/publications/elibrary-page/?id=20645

@inproceedings{Wang2019_20645,
  author = {Wang, Jie and Wang, Dunze and Chen, Yunda and Lu, Xun and Zheng, Chengshi},
  title = {{Noise Robustness Automatic Speech Recognition with Convolutional Neural Network and Time Delay Neural Network}},
  booktitle = {AES Convention 147},
  note = {Paper 10272},
  year = {2019},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20645}
}

TY  - CPAPER
TI  - Noise Robustness Automatic Speech Recognition with Convolutional Neural Network and Time Delay Neural Network
AU  - Wang, Jie
AU  - Wang, Dunze
AU  - Chen, Yunda
AU  - Lu, Xun
AU  - Zheng, Chengshi
T2  - AES Convention 147
M1  - Paper 10272
PY  - 2019
DA  - 2019/10/06
UR  - https://aes.org/publications/elibrary-page/?id=20645
PB  - Audio Engineering Society
LA  - en
AB  - To improve the performance of automatic speech recognition in noisy environments, the convolutional neural network (CNN) combined with time-delay neural network (TDNN) is introduced, which is referred as CNN-TDNN. The CNN-TDNN model is further optimized by factoring the parameter matrix in the time-delay neural network hidden layers and adding a time-restricted self-attention layer after the CNN-TDNN hidden layers. Experimental results show that the optimized CNN-TDNN model has better performance than DNN, CNN, TDNN, and CNN-TDNN. The average recognition word error rate (WER) can be reduced by 11.76% when comparing with the baselines.
ER  -