Title: Modelling the dynamics of acoustic gaps between speakers during business-to-business sales calls
Authors: Anat Lerner; Vered Silber-Varod; Nehoray Carmi; Yonathan Guttel; Omri Allouche
Addresses: Department of Mathematics and Computer Science, The Open University of Israel, Ra'anana, Israel ' Open Media and Information Lab, The Open University of Israel, Ra'anana, Israel ' Open Media and Information Lab, The Open University of Israel, Ra'anana, Israel ' Gong.io, Herzliya, Israel ' Gong.io, Herzliya, Israel
Abstract: The value of conversation intelligence in deepening the insights of authentic conversations is a common ground nowadays between researchers and the business community. The rapid development of big data algorithms and technology enables massive amounts of data and meta-data processing, including content, vocal features and body gestures. This study is based on 358 business-to-business (B2B) sales calls at the discovery stage. We propose a model to capture the dynamics of acoustic gaps between the sales representatives and customers by relying solely on the acoustic signal. We extract basic features from the acoustic signal: speech proportion, fundamental frequency (F0), intensity, harmonics-to-noise ratio (HNR), jitter and shimmer. We focus on the differences between the four speakers' role-gender groups (e.g., female-representative with female-customer). We found significant differences in the behavioural patterns of the dynamics between these four groups. The study demonstrates that using delta metrics to assess the interactions leads to new insights.
Keywords: conversation intelligence; conversation modelling; acoustic features; speech data; sales calls; human spoken interaction; prosodic dynamics; acoustic gaps; computational modelling; conversions metrics.
International Journal of Big Data Intelligence, 2020 Vol.7 No.4, pp.177 - 185
Received: 18 Mar 2020
Accepted: 29 Apr 2020
Published online: 15 Mar 2021 *