Abstract
Accurate assessment and categorization of real-world audio quality in a call, e.g., a call over VoLTE/VoNR, is essential to provide a satisfactory call experience. However, current techniques to determine call quality do not accurately categorize the audio quality. Also, there are no techniques to determine the root cause of poor audio quality or to identify potential solutions. This disclosure describes the use of machine learning clustering techniques to cluster audio metrics and using the obtained clusters to generate a root cause table. Further, a classifier is trained to determine whether an ongoing call has unsatisfactory audio quality. The quality can be categorized and labeled, e.g., good, mildly choppy, severely choppy, and no audio. If the audio quality is unsatisfactory, the likely root cause is identified using the root cause table to identify and apply solutions while the call is in progress. The described techniques are a closed loop technique to identify solutions to audio quality problems in an audio call.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Liu, Yu; Chan, Jack; Zhang, Qin; and Sun, Xiantao, "Call Audio Quality Determination and Root Cause Analysis Using Machine Learning", Technical Disclosure Commons, (March 30, 2023)
https://www.tdcommons.org/dpubs_series/5772