Voice signal detection method, terminal device and storage medium

A voice signal detection method, wherein, the voice signal detection method is applied to a terminal device, the voice signal detection method comprises the following steps:

• receiving a time domain signal detected by a bone conduction sensor in the terminal device, and acquiring a time domain feature in the time domain signal, wherein the bone conduction sensor conducts sound by converting sound into mechanical vibrations of different frequencies, and transmitting sound waves through the human skull, bone labyrinth, inner ear lymph, auger, and auditory center;
• converting the time domain signal into a frequency domain signal, and acquiring a frequency domain feature in the frequency domain signal;
• and
• when the time domain feature satisfies a first preset condition and the frequency domain feature satisfies a second preset condition, determining that a voice signal has been detected by the bone conduction sensor,
• wherein the acquiring the time domain feature in the time domain signal comprises:
• acquiring a short-term zero-crossing rate of the time domain signal;
• and
• acquiring a pitch period of the time domain signal, wherein the time domain feature comprises the short-term zero-crossing rate and the pitch period, and the first preset condition comprises that the short-term zero-crossing rate is greater than a preset short-term zero-crossing rate and the pitch period is greater than a first preset pitch period or smaller than a second preset pitch period, and
• wherein the acquiring the frequency domain feature in the frequency domain signal comprises:
• acquiring a spectral center of gravity of the frequency domain signal, wherein the frequency domain feature comprises the spectral center of gravity, and the second preset condition comprises that the spectral center of gravity is greater than a preset spectral center of gravity.