IEEE Advancing Technology for Humanity;Piscataway: IEEE
摘要:
摘要： This study proposes a speech enhancement method based on compressive sensing. The main procedures involved in the proposed method are performed in the frequency domain. First, an overcomplete dictionary is constructed from the trained speech frames. The atoms of this redundant dictionary are spectrum vectors that are trained by the K-SVD algorithm to ensure the sparsity of the dictionary. For a noisy speech spectrum, formant detection and a quasi-SNR criterion are first utilized to determine whether a frequency bin in the spectrogram is reliable, and a corresponding mask is designed. The mask-extracted reliable components in a speech spectrum are regarded as partial observations and a measurement matrix is constructed. The problem can therefore be treated as a compressive sensing problem. The K atoms of a K-sparsity speech spectrum are found using an orthogonal matching pursuit algorithm. Because the K atoms form the speech signal subspace, the removal of the noise projected onto these K atoms is achieved by multiplying the noisy spectrum with the optimized gain that corresponds to each selected atom. The proposed method is experimentally compared with the baseline methods and demonstrates its superiority. 其他題名： TASLP 出版者： Piscataway: IEEE 出版日期： 2016-11-01 出處： IEEE/ACM transactions on audio, speech, and language processing, 2016-11, Vol.24 (11), p.2122-2131 資源來源： IEEE Electronic Library (IEL) 版權： Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2016 識別號： ISSN: 2329-9290 識別號： EISSN: 2329-9304 識別號： DOI: 10.1109/TASLP.2016.2598306 識別號： CODEN: ITASD8
