Objective Speech Quality Assessment Using Gaussian Mixture Models

@inproceedings{Falk2004ObjectiveSQ,
  title={Objective Speech Quality Assessment Using Gaussian Mixture Models},
  author={Tiago H. Falk and Wai-Yip Chan},
  year={2004}
}
Objective speech quality assessment algorithms provide low-cost and online monitoring of voice calls, replacing costly and timeconsuming subjective listening tests. We propose a novel approach to objective speech quality measurements using Gaussian mixture models (GMMs). A large pool of perceptual distortion features is extracted from speech files and multivariate adaptive regression splines (MARS) is used to sift out the most relevant variables from the pool. The five most salient variables… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-8 of 8 extracted citations

The Transmission Performance in HF Crypto Communication

2008 4th International Conference on Wireless Communications, Networking and Mobile Computing • 2008
View 1 Excerpt

Speech Quality Evaluation: A New Application of Digital Watermarking

IEEE Transactions on Instrumentation and Measurement • 2007
View 2 Excerpts

Speech Quality Evaluation: A New Application of Digital Watermarking

2005 IEEE Instrumentationand Measurement Technology Conference Proceedings • 2005
View 2 Excerpts

Speech quality assessment using digital watermarking

Proceedings. Second International Conference on Creating, Connecting and Collaborating through Computing • 2004

Similar Papers

Loading similar papers…