Abstract | ||
---|---|---|
This paper presents a speech enhancement approach based on speech spectral complex Gaussian Mixture Model (GMM). First, a construction algorithm of speech spectral GMM is introduced and it is based on the distance measure of speech spectral Gaussian probability. Then a noise estimation algorithm based on the GMM is proposed in the Maximum Likelihood criterion using the Expectation-Maximum (EM) algorithm. Speech enhancement experimental results show that the GMM-based MMSE estimators, especially the GMM-based MMSE short-time spectral estimator, can afford better performance than alternative speech enhancement algorithms and the proposed noise estimation algorithm can improve the enhancement performance more, especially at low SNRs. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICASSP.2005.1415076 | 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING |
Keywords | Field | DocType |
spectral estimation,gaussian mixture model,acoustic noise,clustering algorithms,maximum likelihood estimation,gaussian processes,maximum likelihood,speech processing,hidden markov models,gaussian distribution,probability,em algorithm,data mining | Speech enhancement,Speech processing,Pattern recognition,Expectation–maximization algorithm,Computer science,Speech recognition,Gaussian,Gaussian process,Artificial intelligence,Hidden Markov model,Mixture model,Estimator | Conference |
Volume | Issue | ISSN |
I | null | 1520-6149 |
Citations | PageRank | References |
2 | 0.38 | 6 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Guo-Hong Ding | 1 | 27 | 4.99 |
Xia Wang | 2 | 2 | 0.38 |
Yang Cao | 3 | 3 | 0.79 |
Feng Ding | 4 | 3 | 0.79 |
Yuezhong Tang | 5 | 34 | 5.99 |