Patent

The present invention is enclosed in the area of Quality of Service (QoS) in audio communications, in particular voice communications, over priority-enabled networks, when poor transmission conditions occur. It is therefore an object of the present invention a method for optimal classification of a utterance U of a digital audio signal, such utterance being segmented in n segments, comprising i) a phase of ordered candidate segment identification, and ii) a further phase of recursive determination of an optimal m-subset with m positions, whereby the m-subset is equalled to said recursively determined subset, and a higher priority value is associated with the segments of the m-subset. The method of the present invention achieves higher Mean Opinion Scores (MOS) in comparison with non-selective packet drop under the same random network loss conditions, yielding better QoS for the same packet loss rates (PLR).