Page 116 - 201806

946 2018 年 11 月

Hou Yimin, Zhou Huiqiong, Wang Zhengyi. Overview of (ICASSP), 2016 IEEE International Conference on.
speech recognition based on deep leaarning[J]. Application IEEE, 2016: 4955–4959.
Research of Computers, 2017, 34(8): 2241–2246. [10] Sainath T N, Kingsbury B, Saon G, et al. Deep con-
[3] Li J, Mohamed A, Zweig G, et al. LSTM time volutional neural networks for large-scale speech tasks[J].
and frequency recurrence for automatic speech recogni- Neural Networks, 2015, 64: 39–48.
tion[C]//Automatic Speech Recognition and Understand- [11] Yu D, Xiong W, Droppo J, et al. Deep convolutional neu-
ing, IEEE, 2016: 187–191. ral networks with layer-wise context expansion and atten-
[4] Mohamed A, Dahl G, Hinton G. Deep belief networks for tion[C]// Interspeech, 2016: 17–21.
phone recognition[C]//Nips Workshop on Deep Learning [12] Qian Y, Bi M, Tan T, et al. Very deep convolutional
for Speech Recognition and Related Application, 2009: neural networks for noise robust speech recognition[J].
39. IEEE/ACM Transactions on Audio Speech & Language
[5] Sainath T N, Vinyals O, Senior A, et al. Convolutional, Processing, 2016, 24(12): 2263–2276.
long short-term memory, fully connected deep neural net- [13] 梁玉龙, 屈丹, 李真, 等. 基于卷积神经网络的维吾尔语语音
works[C]//IEEE International Conference on Acoustics, 识别 [J]. 信息工程大学学报, 2017, 18(1): 44–50.
Speech and Signal Processing IEEE, 2015: 4580–4584. Liang Yulong, Qu Dan, Li Zhen, et al. Uyghur speech
[6] 孙艳丰, 齐光磊, 胡永利, 等. 基于改进 Fisher 准则的深度 recognition based on convolutional neural network[J].
卷积神经网络识别算法 [J]. 北京工业大学学报, 2015, 41(6): Journal of Information Engineering University, 2017,
835–841. 18(1): 44–50.
Sun Yanfeng, Qi Guanglei, Hu Yongli, et al. Deep con- [14] 黄玉蕾, 罗晓霞, 刘笃仁. MFSC 系数特征局部有限权重共享
volution neural network recognition algorithm based on CNN 语音识别 [J]. 控制工程, 2017, 24(7): 1507–1513.
improved Fisher criterion[J]. Journal of Beijing University Huang Yulei, Luo Xiaoxia, Liu Duren. Local finite
of Technology, 2015, 41(6): 835–841. weight sharing of MFSC coefficients based CNN speech
[7] Sainath T N, Mohamed A R, Kingsbury B, et al. Deep recognition[J]. Control Engineering of China, 2017, 24(7):
convolutional neural networks for LVCSR[C]//IEEE In- 1507–1513.
ternational Conference on Acoustics, Speech and Signal [15] Hori T, Watanabe S, Zhang Y, et al. Advances in joint
Processing, IEEE, 2013: 8614–8618. CTC-attention based end-to-end speech recognition with
[8] Huang J T, Li J, Gong Y. An analysis of convolutional a deep CNN encoder and RNN-LM[J]. arXiv preprint
neural networks for speech recognition[C]//IEEE Inter- arXiv: 1706.02737, 2017.
national Conference on Acoustics, Speech and Signal Pro- [16] Zeiler S, Nicheli R, Ma N, et al. Robust audiovi-
cessing, IEEE, 2015: 4989–4993. sual speech recognition using noise-adaptive linear dis-
[9] Sercu T, Puhrsch C, Kingsbury B, et al. Very criminant analysis[C]//IEEE International Conference on
deep multilingual convolutional neural networks for Acoustics, Speech and Signal Processing, IEEE, 2016:
LVCSR[C]//Acoustics, Speech and Signal Processing 2797–2801.