Content-based Compressive Sensing for Speech Signal

Compressive sensing theory compress measurements using sparsity of signal, changes the method of signal obtaining from signal sampling to information sensing, and is a revolution of signal processing. The speech signal is sparse represented based on Uncertainty Basis Dictionary proposed in this paper, the sparse representation of speech signal is compressed by compressive sensing theory，and proposes an speech signal reconstruction algorithm based on the method of solving linear programming problem. Through the experiments of audio, speaker and emotion recognition, we research that this information sensing method based on compressive sensing theory weather preserves the main content from the angle of content-based analysis. Experiment results show that the precision of audio, speaker and emotion recognition is general the same with methods in these research domain, and proves that it can acquire the audio, speaker and emotion information of speech signal using the information sensing method based on compressive sensing theory.