Data Augmentation for Internet of Things Dialog System
- PDF / 1,286,088 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 12 Downloads / 221 Views
Data Augmentation for Internet of Things Dialog System Eric Ke Wang 1 & Juntao Yu 1 & Chien-Ming Chen 2 & Saru Kumari 3
&
Joel J. P. C. Rodrigues 4,5
# Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract With rapid development of voice control technology, making speech recognition more precisely in various IoT domains have been an intractable problem to be solved. Since there are various conversation scenes, understanding the context of a dialog scene is a key issue of voice control systems. However, the reality is available training data for dialog system are always insufficient. In this paper, we mainly solve the problem of data lacking in dialog systems by data augmentation technique. A Generative Adversarial Network(GAN)-based model is proposed and the data are augmented effectively. It can generate from text to text, enhance the original data with text retelling, and improve the robustness of parameter estimation of unknown data by using the sample data generated by GAN model. A new N-gram language model is used to evaluate multiple recognition candidates of speech recognition, and the candidate sentences with the highest evaluation scores are selected as the final result of speech recognition. Our data enhancement algorithm based on the Generative Model is verified by the experiments. In the result of model comparison test, the error rates of data set THCHS30 and AISHELL are 3.3% and 5.1% which are lower than that of the baseline system. Keywords GAN . Data augmentation . CNN . Dialog system
1 Introduction Voice control technology of the Internet of things(IoT) is now entering all aspects of life, for example, automobile is in the leading position in the application of IoT. In 2020, Gartner predicts that one in five cars will be connected to the Internet
* Saru Kumari [email protected] Eric Ke Wang [email protected] Juntao Yu [email protected] Chien-Ming Chen [email protected] Joel J. P. C. Rodrigues [email protected] 1
Harbin Institute of Technology, Shenzhen, Harbin, China
2
College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, Shandong, China
3
Department of Mathematics, Chaudhary Charan Singh University, Meerut, India
4
Federal University of Piauí, Teresina, PI 64049-550, Brazil
5
Instituto de Telecomunicações, Aveiro, Portugal
[1, 2]. Both Google and Apple have tools that allow drivers to use voice control system to control their phones, listen to messages and control apps. The intelligent cars enable drivers to control the radio by voice so as not to be distracted when driving. The combination of voice control and smart home makes it control smart home devices. It can integrate almost all aspects of smart home devices- refrigerators, lamps, televisions, washing machines, etc. With more and more devices connected to the Internet, voice commands will control more and more smart devices. Besides, medical records can be updated in real time using smart speakers or digital assistants. An Alexa app cal
Data Loading...
