Jitter buffer control based on monitoring of delay jitter and conversational dynamics

Abstract

Some implementations involve analyzing audio packets received during a time interval that corresponds with a conversation analysis segment to determine network jitter dynamics data and conversational interactivity data. The network jitter dynamics data may provide an indication of jitter in a network that relays the audio data packets. The conversational interactivity data may provide an indication of interactivity between participants of a conversation represented by the audio data. A jitter buffer size may be controlled according to the network jitter dynamics data and the conversational interactivity data. The time interval may include a plurality of talkspurts.

1 . A method, comprising:
 receiving audio data frames, the audio data frames included in audio data packets received at actual packet arrival times during a time interval that corresponds with a conversation analysis segment;   analyzing the audio data of the conversation analysis segment to determine network jitter dynamics data and conversational interactivity data, wherein the network jitter dynamics data provides an indication of jitter in a network that relays the audio data packets and wherein the conversational interactivity data provides an indication of interactivity between participants of a conversation represented by the audio data frame;   selecting, based on the network jitter dynamics and the conversational interactivity data of the audio data, a jitter buffer control mode from at least three jitter buffer control modes, wherein each jitter buffer control mode corresponds to a range of jitter buffer sizes; and   determining a jitter buffer size based on the selected jitter buffer control mode.   
     
     
         2 . The method of  claim 1 , wherein determining the jitter buffer size comprises adaptively varying the jitter buffer size within the range of sizes for the selected jitter buffer control mode. 
     
     
         3 . The method of  claim 1 , wherein the at least three jitter buffer control modes include a peak mode, a low-loss mode and a normal mode,
 wherein the peak mode is determined by using inter-percentile, IPR, calculations, delay spike intensity and/or spike presence probability,   wherein the low-loss mode is related to a presentation mode,   wherein the normal mode is a non-peak mode and non-presentation mode.   
     
     
         4 . An apparatus configured to perform the method of  claim 1 . 
     
     
         5 . A computer program product having instructions which, when executed by a computing device or system, cause said computing device or system to perform the method of  claim 1 .