Title | ||
---|---|---|
Predicting Tongue Motion In Unlabeled Ultrasound Videos Using Convolutional Lstm Neural Networks |
Abstract | ||
---|---|---|
A challenge in speech production research is to predict future tongue movements based on a short period of past tongue movements. This study tackles speaker-dependent tongue motion prediction problem in unlabeled ultrasound videos with convolutional long short-term memory ( ConvLSTM) networks. The model has been tested on two different ultrasound corpora. ConvLSTM outperforms 3-dimensional convolutional neural network ( 3DCNN) in predicting the 9th frames based on 8 preceding frames, and also demonstrates good capacity to predict only the tongue contours in future frames. Further tests reveal that ConvLSTM can also learn to predict tongue movements in more distant frames beyond the immediately following frames. Our codes are available at: https://github.com/shuiliwanwu/ConvLstm-ultrasoundvideos. |
Year | Venue | Keywords |
---|---|---|
2019 | 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | convolutional recurrent neural network, motion prediction, speech production, ultrasound tongue imaging, silent speech interface |
Field | DocType | Volume |
Task analysis,Pattern recognition,Convolutional neural network,Computer science,Linear programming,Artificial intelligence,Silent speech interface,Artificial neural network,Speech production,Tongue,Ultrasound | Journal | abs/1902.06927 |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
4 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chaojie Zhao | 1 | 0 | 0.34 |
Peng Zhang | 2 | 0 | 0.34 |
Jian Zhu | 3 | 15 | 4.11 |
Chengrui Wu | 4 | 0 | 0.34 |
Wang Huaimin | 5 | 1025 | 121.31 |
Kele Xu | 6 | 46 | 21.80 |