Automatic Gain Adjustment Circuit

Abstract

The invention discloses an automatic gain adjustment circuit. The automatic gain adjustment circuit comprises a variable gain amplification circuit, a comparison voltage generation circuit and a signal detection circuit, wherein the variable gain amplification circuit receives voice signals input from the outside, amplifies the voice signals and outputs the amplified voice signals, the comparison voltage generation circuit generates a reference voltage and loads the reference voltage to the signal detection circuit, the signal detection circuit detects the deviation between the amplitude of the voice signals output after comparison and a set amplitude, and when the amplitude of the voice signals output by the variable gain amplification circuit deviates from the set amplitude, the signal detection circuit feeds a varied voltage back to the variable gain amplification circuit. The variable gain amplification circuit adjusts the amplitude of the voice signals output by the variable gain amplification circuit according to the varied voltage, and the amplitude of the voice signals output by the variable gain amplification circuit is made to be the same as the set amplitude. After the automatic gain adjustment circuit receives the voice signals output from the outside, a stable voice signal with the amplitude the same as the set amplitude is output, and the identification accuracy of the received voice signals is improved.

Description

technical field [0001] The present invention relates to the field of speech recognition, and more particularly relates to an automatic gain adjustment circuit. Background technique [0002] When utilizing the voice recognition chip for voice recognition, the distance between the position of the sound source as the signal source and the voice recognition chip is variable, and the commonly used voice recognition system is to amplify and output the input voice signal by a fixed multiple; The speech recognition system with fixed magnification causes the following problems: when the position of the sound source is very close to the speech recognition system, because the speech signal detected by the speech recognition chip has a large amplitude, after passing through the amplifier with a fixed multiple, it will cause the output speech signal clipping; however, when the sound source is far away from the speech recognition system, since the speech signal amplitude decreases exponen...

AI Technical Summary

Problems solved by technology

[0002] When utilizing the voice recognition chip for voice recognition, the distance between the position of the sound source as the signal source and the voice recognition chip is variable, and the commonly used voice recognition system is to amplify and output the input voice signal by a fixed multiple; The speech recognition system with fixed magnification causes the following problems: when the position of the sound source is very close to the speech recognition system, because the speech signal detected by the speech recognition chip has a large amplitude, after passing through the amplifier with a fixed multiple, it will cause the output speech signal clipping; however, when the sound source is far away from the speech recognition system, since the speech signal amplitude decreases exponentially with the increase of the distance, the signal amplitude amplified by the amplifier with a fixed magnification factor is still very small, thus Difficult to meet design requirements

Therefore, the above two situations will seriously affect the recognition accuracy of the speech recognition system.

Images