A Recurrent Neural Network Approach to the Answering Machine Detection Problem

TL;DR

This paper introduces a real-time answering machine detection method using transfer learning with YAMNet and recurrent neural networks, achieving over 96% accuracy and potential improvements with silence detection.

Contribution

It presents a novel real-time answering machine detection approach leveraging transfer learning and recurrent neural networks, with high accuracy and analysis of misclassifications.

Findings

Over 96% accuracy on test data

Silence detection can increase accuracy above 98%

Real-time processing enabled by recurrent architecture

Abstract

In the field of telecommunications and cloud communications, accurately and in real-time detecting whether a human or an answering machine has answered an outbound call is of paramount importance. This problem is of particular significance during campaigns as it enhances service quality, efficiency and cost reduction through precise caller identification. Despite the significance of the field, it remains inadequately explored in the existing literature. This paper presents an innovative approach to answering machine detection that leverages transfer learning through the YAMNet model for feature extraction. The YAMNet architecture facilitates the training of a recurrent-based classifier, enabling real-time processing of audio streams, as opposed to fixed-length recordings. The results demonstrate an accuracy of over 96% on the test set. Furthermore, we conduct an in-depth analysis of misclassified samples and reveal that an accuracy exceeding 98% can be achieved with the integration of a silence detection algorithm, such as the one provided by FFmpeg.