In this paper the robustness of Network Speech Recogni- tion (NSR) systems is analyzed. In NSR the speech signal is transmitted using a conventional speech codec from the client to the server, where the recognition task is carried out. The use of speech codecs degrades the performance of such systems, mainly in presence of acoustic noise and packet losses. First, we study the effects of possible degradation sources. Then, we propose a new NSR solution based on a robust feature extractor and an efficient packet loss concealment (PLC) algorithm, which compensates the possible degradations by means of a cepstral compensation and linear interpolation. The experimental results are obtained for a well-known speech codec, AMR 12.2 kbps, using a noisy database (Aurora-2) and several packet loss conditions. The results show that our proposal achieves noticeable improvements over the baseline results. Index Terms: Network speech recognition, robust speech recognition, packet loss concealment.