Speech endpoint detection in strong noisy environment based on the Hilbert-Huang Transform

Speech endpoint detection in strong noise environment plays an important role in speech signal processing. Hilbert-Huang Transform (HHT) is based on the local characteristics of signals, which is an adaptive and efficient transformation method. It is particularly suitable for analyzing the non-linear and non-stationary signals such as speech signal. In this paper, we chose the noisy speech signal when the signal-to-noise ratio is negative. A novel algorithm for speech endpoint detection based on Hilbert-Huang transform is provided after analyzing the noisy speech signal. The signal is first decomposed by Empirical Mode Decomposition (EMD), and partial decomposition results are processed by Hilbert transform. The threshold of noise is estimated by analyzing the front of signal´s Hilbert amplitude spectrum. The speech segments and non-speech segments can be distinguished by the threshold and the whole signal´s Hilbert amplitude spectrum. Simulation results show that the speech signal can be effective detected by this algorithm at low signal-to-noise ratio.