This work presents the results of a psycho-physical experiment in which a group of forty (40) human participants rated the overall quality of a set of 40 high-definition audio-visual sequences. These audio-visual sequences were impaired with audio and video types of distortions commonly encountered in an Internet-based transmission scenario. More specifically, Packet-Loss and Frame Freezing distortions were added to the video component, while Background noise, Chop, Clipping, and Echo distortions were added to the audio component. Our goal was to study how audio and visual degradations interact with each other and with the content to produce the overall audio-visual quality. An immersive experimental methodology was used to obtain more accurate observer scores. Preliminary results show that the audio and video degradations interact with each other to produce the overall audio-visual quality. For different types of audio degradations, the Clip degradation obtained slightly lower quality scores. Similarly, for the different video degradations, Framefreezing distortions were rated higher. Also, when audio degradations were combined with Packet-loss, they had a stronger impact on the audio-visual quality.