Design and Construction of Intelligent Voice Control System
325
Fig. 4. Character correct ratio and word correct ratio
5 Conclusion
In the paper, we propose an intelligent voice control system which can realize the
functions of voice activity detection, speech recognition, speaker authentication,
instruction analysis, and automatic answer, performing us the good extension
of artificial intelligent. In order to decrease system delay and increase correct
recognition rate, we propose new VAD algorithm and backtracking algorithm;
We contrast four model label plan and choose the fourth plan which uses initial and tonal final combination two-variable label method because of its good
performance. Finally, we test our system in our own simulation corpus and the
results are satisfactory. In the next work, we will test our system in an actual
environment and update the system to improve its performance.
References
1. Peng Y, Zhang J, Chen R, Ren S (2017) A specific speech control home system.
Comput Sci Appl 10:935–943
2. Niu S, Tang W (2018) Design of Chinese text and audio editing system based on
AI. Content production and broadcasting, vol 45, pp 56–61
3. WebRTC. http://webrtc.org/
4. Jurafsky D, Martin JH (2018) An introduction to natural language processing, computational linguistic, and speech recognition
5. Chinese text segmentation. https://github.com/fxsjy/jieba
325
Fig. 4. Character correct ratio and word correct ratio
5 Conclusion
In the paper, we propose an intelligent voice control system which can realize the
functions of voice activity detection, speech recognition, speaker authentication,
instruction analysis, and automatic answer, performing us the good extension
of artificial intelligent. In order to decrease system delay and increase correct
recognition rate, we propose new VAD algorithm and backtracking algorithm;
We contrast four model label plan and choose the fourth plan which uses initial and tonal final combination two-variable label method because of its good
performance. Finally, we test our system in our own simulation corpus and the
results are satisfactory. In the next work, we will test our system in an actual
environment and update the system to improve its performance.
References
1. Peng Y, Zhang J, Chen R, Ren S (2017) A specific speech control home system.
Comput Sci Appl 10:935–943
2. Niu S, Tang W (2018) Design of Chinese text and audio editing system based on
AI. Content production and broadcasting, vol 45, pp 56–61
3. WebRTC. http://webrtc.org/
4. Jurafsky D, Martin JH (2018) An introduction to natural language processing, computational linguistic, and speech recognition
5. Chinese text segmentation. https://github.com/fxsjy/jieba