Name
Abstract | ||
|---|---|---|
In this paper, we evaluate the performance of several objective measures in terms of predicting the quality of noisy speech enhanced by noise suppression algorithms. The objective measures considered a wide range of distortions introduced by four types of real-world noise at two signal-to-noise ratio levels by four classes of speech enhancement algorithms: spectral subtractive, subspace, statistical-model based, and Wiener algorithms. The subjective quality ratings were obtained using the ITU-T P.835 methodology designed to evaluate the quality of enhanced speech along three dimensions: signal distortion, noise distortion, and overall quality. This paper reports on the evaluation of correlations of several objective measures with these three subjective rating scales. Several new composite objective measures are also proposed by combining the individual objective measures using nonparametric and parametric regression analysis techniques. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1109/TASL.2007.911054 | IEEE Transactions on Audio, Speech & Language Processing |
Keywords | Field | DocType |
stochastic processes,enhanced speech,nonparametric-parametric regression analysis,objective measure,noise distortion,speech quality assessment,objective quality measures,correlation method,wiener algorithm,subspace algorithm,regression analysis,new composite objective measure,distortion,spectral subtractive algorithm,real-world noise,overall quality,spectral analysis,signal distortion,noise suppression algorithm,subjective quality rating,statistical model based algorithm,subjective listening tests,objective speech quality measure evaluation,objective measures,interference suppression,noisy speech,speech enhancement,individual objective,correlation methods,signal to noise ratio,three dimensions,statistical model,noise,noise measurement,correlation,rating scale,speech,indexing terms,prediction algorithms | Speech enhancement,Noise reduction,Speech processing,Noise measurement,Pattern recognition,Computer science,Signal-to-noise ratio,Sound quality,Speech recognition,Artificial intelligence,Distortion,PESQ | Journal |
Volume | Issue | ISSN |
16 | 1 | 1558-7916 |
Citations | PageRank | References |
487 | 25.67 | 10 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Y. Hu | 1 | 1098 | 69.42 |
| P. C. Loizou | 2 | 863 | 71.05 |