TY - GEN
T1 - An Improved LSTM for Language Identification
AU - Zhan, Qingran
AU - Zhang, Liqiang
AU - Deng, Hui
AU - Xie, Xiang
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2019/2/2
Y1 - 2019/2/2
N2 - In this paper, we propose a novel framework by combining the phonetic temporal neural model (PTN) with an improved LSTM (IM-LSTM). This is achieved by using an up-down connection from the time t to t+1 in the LSTM structure, which aims to capture the latent information from the previous time step. This updated structure can perform better to discriminate the frame-level phonetic information produced by PTN. On the AP16-OLR language identification dataset, our final model achieves relative growth rate 5.04%, 2.19%, 2.73% on EER and 6.55%, 5.81%, 2.23% on Cavg in 1s, 3s and full-length utterance condition than the standard PTN, respectively. The proposed framework receives a better performance than the standard PTN and other proposed models, particularly in 1s condition. This shows the efficacy and flexibility of the proposed method.
AB - In this paper, we propose a novel framework by combining the phonetic temporal neural model (PTN) with an improved LSTM (IM-LSTM). This is achieved by using an up-down connection from the time t to t+1 in the LSTM structure, which aims to capture the latent information from the previous time step. This updated structure can perform better to discriminate the frame-level phonetic information produced by PTN. On the AP16-OLR language identification dataset, our final model achieves relative growth rate 5.04%, 2.19%, 2.73% on EER and 6.55%, 5.81%, 2.23% on Cavg in 1s, 3s and full-length utterance condition than the standard PTN, respectively. The proposed framework receives a better performance than the standard PTN and other proposed models, particularly in 1s condition. This shows the efficacy and flexibility of the proposed method.
KW - LSTM
KW - Language identification
KW - Temporal information
UR - http://www.scopus.com/inward/record.url?scp=85063263366&partnerID=8YFLogxK
U2 - 10.1109/ICSP.2018.8652445
DO - 10.1109/ICSP.2018.8652445
M3 - Conference contribution
AN - SCOPUS:85063263366
T3 - International Conference on Signal Processing Proceedings, ICSP
SP - 609
EP - 612
BT - 2018 14th IEEE International Conference on Signal Processing Proceedings, ICSP 2018
A2 - Baozong, Yuan
A2 - Qiuqi, Ruan
A2 - Yao, Zhao
A2 - Gaoyun, An
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IEEE International Conference on Signal Processing, ICSP 2018
Y2 - 12 August 2018 through 16 August 2018
ER -