Methods for Evaluation of Speech Enhancement Algorithms
Keywords:
combat vehicle, communication system, speech enhancement, speech quality, quality measure, MOS, DAM, ITU-T P.835, Itakura-Saito measure, PESQAbstract
Communication systems play the key role in contemporary combat operations. These systems, which can be either onboard or man-wearable, are working in very noisy environment. The noise coming from the vehicle itself and onboard combat systems is entering communication channel via microphones of personal headsets and handsets. Thanks to digital speech processing algorithms it is possible to suppress these annoying background signals. This can be done with speech enhancement algorithms. The target is to gain clear speech of high intelligibility and high quality. This paper presents the methods generally recommended for the evaluation of speech enhancement algorithms in terms of speech quality. Thanks to this knowledge, the best speech enhancement algorithm can be found in practice.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Users can use, reuse and build upon the material published in the journal for any purpose, even commercially.
