User-defined instruction recognition speech photographing system

Abstract

The invention discloses an user-defined instruction recognition speech photographing system, the system comprises a speech instruction collecting module, an audio signal preprocessing module, an audio signal feature extraction module, a speech definition training module and a speech recognition control module, the speech instruction collecting module is used for collecting audio signals of a speech instruction; preprocessing and feature extraction are performed on the collected audio signal through the audio signal preprocessing module and the audio signal feature extraction module in sequence; the speech definition training module is used for establishing a speech feature pattern library and logging the speech instruction corresponding to the processed and extracted audio signal in the feature pattern library; and the speech recognition control module searches a minimum matching error to obtain a recognition result and executes the corresponding speech instruction. The technical scheme disclosed by the invention can improve the practicability of speech photographing function and can realize user personalized customization, and the interactivity between the user and the device can be improved.

Description

technical field [0001] The invention discloses a voice photographing system capable of self-defining instruction recognition and relates to the technical field of audio signal processing. Background technique [0002] With the rapid development of the information industry, intelligent products have been widely favored by people. As a key technology of human-computer interaction, speech recognition has been applied in many aspects of our lives, such as car voice navigation, mobile phone voice-activated dialing, home appliance control and voice database retrieval services, etc. [0003] In the intelligent product market, mobile phones occupy an important position because of their lightness, dexterity and rich APP functions. Among them, various camera software has been favored by the majority of users, and their functions are constantly evolving and improving. It is not difficult to find that in many camera software, there is basically a voice camera function, which mainly con...

AI Technical Summary

Problems solved by technology

However, these voice commands are generally specified by the system, that is to say, the user can only realize voice photography through fixed voice commands.

This will inevitably cause certain limitations. First of all, everyone's different speaking styles, different pronunciations, and the existence of dialects may lead to the failure of the specified voice command recognition.

Secondly, when the user wants to take a selfie by voice, considering that everyone’s smile is not the same, therefore, the selfie effect achieved by using the same voice command may not meet the requirements of each user at the same time, for example: some people The best smiles come when you use the voice command “eggplant,” while others prefer “tomato,” “cheese,” or “Kimci” (the Korean word for “kimchi”), etc.

In the prior art, there are relatively few methods or systems in which users can customize voice commands to identify and control the camera to take pictures

Images