Human and Machine Speaker Recognition Based on Short Trivial Events

TL;DR

This study explores the potential of trivial speech events like coughs and laughs for speaker recognition, demonstrating that even short, unclear sounds can be used effectively for identification with deep learning methods.

Contribution

The paper introduces a novel trivial event speech database and applies deep feature learning to achieve promising speaker recognition results from very short speech segments.

Findings

Deep learning achieves acceptable EERs on trivial events

'Hmm' is more speaker discriminative among event types

Trivial events can aid forensic speaker identification

Abstract

Trivial events are ubiquitous in human to human conversations, e.g., cough, laugh and sniff. Compared to regular speech, these trivial events are usually short and unclear, thus generally regarded as not speaker discriminative and so are largely ignored by present speaker recognition research. However, these trivial events are highly valuable in some particular circumstances such as forensic examination, as they are less subjected to intentional change, so can be used to discover the genuine speaker from disguised speech. In this paper, we collect a trivial event speech database that involves 75 speakers and 6 types of events, and report preliminary speaker recognition results on this database, by both human listeners and machines. Particularly, the deep feature learning technique recently proposed by our group is utilized to analyze and recognize the trivial events, which leads to acceptable equal error rates (EERs) despite the extremely short durations (0.2-0.5 seconds) of these events. Comparing different types of events, 'hmm' seems more speaker discriminative.