Research on voice control and virtual testing of marine engine systems

Abstract Speech recognition, as an important research direction in artificial intelligence technology, is widely used in various industrial fields. Under this trend, intelligent technologies such as speech recognition will also become research hotspots in the field of marine engineering. Moreover, as voice interaction is expected to become the main method of human-computer interaction in the future, the exploration of voice control for marine engine systems is of great significance. A speech recognition model is established based on CNN-LSTM-Transformer and CTC. Compared with the traditional statistical model and a single neural network model, it improves its robustness and is more suitable for real cabin environment. The flow instruction set is established, and the voice control instruction is decomposed into low-level control instructions that can be recognized by the ship system to achieve highly centralized control. Virtual testing of voice commands based on marine engine simulators. The accuracy of voice control in a virtual noisy environment is 92%, which can meet its control requirements in marine systems.