The invention discloses a speech signal time delay estimation method and system used for echo cancellation. The method comprises the following steps of respectively obtaining a far-end signal and a near-end signal of a voice signal received by a microphone in a call and generating a corresponding far-end frequency domain signal and a corresponding near-end frequency domain signal; adopting a critical band based on the auditory masking effect to respectively carry out sub-band decomposition in the frequency band on the far-end frequency domain signal and the near-end frequency domain signal and obtaining a power spectrum of each critical frequency point of the far-end frequency domain signal and a power spectrum of each critical frequency point of the near-end frequency domain signal; respectively extracting local binary features of the power spectrum of each critical frequency point of the far-end frequency domain signal and the power spectrum of each critical frequency point of the near-end frequency domain signal, respectively matching and generating and outputting a time delay estimation result. According to the method and the system, the correlation between the far-end signal and the near-end signal is counted based on the auditory masking effect, the computation is simple, and the accurate time delay estimation can be obtained to bring great convenience for echo cancellation.