Hybrid Feature Selection Approach for Natural Language Call Routing Systems

Abstract

Call routing based on natural language identification is an important issue for call centres operating in a multilingual scenario. This is due to the fact that it is not possible for a human agent to become fluent in all languages. In this paper, we propose a call routing system based on prosodic and phonetic features to improve the performance of automatic call routing systems. The main focus of this paper is to propose a feature set that efficiently improves the performance of the system without incorporating several sets of features. Our proposed approach for combining the prosodic and phonetic features achieves an accuracy rate of 98.36% for a binary language identification call routing system.