# Speaker Recognition with Cough, Laugh and "Wei"

## TL;DR

This paper explores speaker recognition using trivial speech events like cough, laugh, and

## Contribution

It introduces a deep feature learning approach that effectively extracts speaker information from short, non-verbal speech events, achieving promising recognition performance.

## Key findings

- Rich speaker information exists in trivial events.
- Deep features enable 10%-14% EER on short events.
- Effective recognition despite short duration (0.2-1.0s).

## Abstract

This paper proposes a speaker recognition (SRE) task with trivial speech events, such as cough and laugh. These trivial events are ubiquitous in conversations and less subjected to intentional change, therefore offering valuable particularities to discover the genuine speaker from disguised speech. However, trivial events are often short and idiocratic in spectral patterns, making SRE extremely difficult. Fortunately, we found a very powerful deep feature learning structure that can extract highly speaker-sensitive features. By employing this tool, we studied the SRE performance on three types of trivial events: cough, laugh and "Wei" (a short Chinese "Hello"). The results show that there is rich speaker information within these trivial events, even for cough that is intuitively less speaker distinguishable. With the deep feature approach, the EER can reach 10%-14% with the three trivial events, despite their extremely short durations (0.2-1.0 seconds).