Measuring social ambiance in unconstrained environments is of significant importance in mental health due to the association between sociability and psychological outcome. However, it has been challenging to quantify social ambiance since existing objective methods fail to capture the transient ambiance patterns in unconstrained environments. In this thesis, I present AmbianceCount, an automatic and objective method that extracts social ambiance from unconstrained audio recordings by estimating the number of concurrent speakers. AmbianceCount consists of a supervised deep neural network (DNN) embedding extractor to differentiate speech mixtures, and a scoring system for estimation and improving generalization. The performance of Am- bianceCount is compared with baseline and evaluated on several synthesized datasets. Lastly, I utilize AmbianceCount to evaluate data from a sociability pilot, with audio data from depression and psychosis patients as well as age-matched healthy controls. Our analysis shows that extracted social ambiance patterns are significantly different across three groups. Besides, it is observed that captured social ambiance patterns are associated with psychometric and personality scores, which is consistent with clinical diagnosis.