Traditional speech detection methods regard the noise as a jamming signal to filter, but under the strong noise background, these methods lost part of the original speech signal while eliminating noise. Stochastic resonance can use noise energy to amplify the weak signal and suppress the noise. According to stochastic resonance theory, a new method based on adaptive stochastic resonance to extract weak speech signals is proposed. This method, combined with twice sampling, realizes the detection of weak speech signals from strong noise. The parameters of the system a, b are adjusted adaptively by evaluating the signal-to-noise ratio of the output signal, and then the weak speech signal is optimally detected. Experimental simulation analysis showed that under the background of strong noise, the output signal-to-noise ratio increased from the initial value-7 dB to about 0.86 dB, with the gain of signal-to-noise ratio is 7.86 dB. This method obviously raises the signal-to-noise ratio of the output speech signals, which gives a new idea to detect the weak speech signals in strong noise environment.