Deep learning based automatic volume control and limiter system

Automatic speech recognition is now playing an important role in volume control and adjustment of modern smart speakers. According to the recognition results by using the advanced deep neural network technology, this paper proposes an efficient processing system for automatic volume control (AVC) and limiter. The theoretical analyses, subjective and objective testing results show that the proposed processing system can offer a significant improvement for speech recognition performance during audio playback and improvement for audio playback performance in smart speakers. Driven by input data and audio contents, the proposed AVC is able to adaptively learn and track an effective signal level at the speed corresponding to the width of transient sound; the adaptation is frozen in the case of silence and noise periods. The proposed limiter measures the peaks and can guarantee that no peak will go over the predetermined peak threshold so as to avoid clipping and harmonic distortions.