Intelligent voice control method applied in electric power field

Abstract

The intelligent voice control method applied in the electric power field proposed by the embodiment of the present application includes extracting key voice waveforms including device control instructions and environmental noise waveforms from the received voice signal waveforms; superimposing and reducing the key voice waveforms based on the environmental noise waveforms Noise; according to the peak duration of the key voice waveform after noise reduction, the command sentence sentence processing is carried out to obtain the command sentence waveform for equipment operation; combined with the equipment operation proper noun library, the command text corresponding to each command sentence waveform is determined, and according to the equipment control Instruction statement structure obtains the key elements of each instruction text to construct standardized equipment regulation instructions. Segmenting the voice waveform based on the peak duration can effectively ensure that the waveform after the sentence is corresponding to a complete command, and then convert the command text according to the voice waveform after the sentence, and obtain more accurate equipment control instructions. Thereby improving the accuracy of equipment control.

Description

technical field [0001] The present application relates to the field of voice processing, in particular to an intelligent voice control method applied in the electric power field. Background technique [0002] Ensuring the safe and stable operation of the power grid is an important part of the basic and important links of power supply and other industry services. As the scale of the power grid continues to expand, the workload related to dispatching will also increase exponentially, which will take more and more energy from the regulators. At present, speech recognition technology is being gradually applied to power grid dispatching work. However, the theoretical assumptions of traditional speech recognition methods are very different from the actual situation, so it is difficult to achieve the expected performance in practical applications. Deep learning is an important machine learning theory for big data processing, which has important reference significance for speech re...

AI Technical Summary

Problems solved by technology

However, the theoretical assumptions of traditional speech recognition methods are very different from the actual situation, so it is difficult to achieve the expected performance in practical applications, and deep learning is an important machine learning theory for big data processing, which has important reference significance for speech recognition

Images