Haha-Pod: An Attempt for Laughter-based Non-Verbal Speaker Verification

TL;DR

This paper investigates the potential of laughter as a non-verbal cue for speaker verification, introducing a new dataset and a two-stage teacher-student framework that enhances identification accuracy using laughter signals.

Contribution

It presents the Haha-Pod dataset of laughter clips and verbal speech, and proposes a novel Two-Stage Teacher-Student framework for laughter-based speaker verification.

Findings

Significant improvement in laughter-based speaker verification accuracy.

Minor performance degradation on traditional verbal speech verification.

Introduction of a new laughter dataset for speaker recognition research.

Abstract

It is widely acknowledged that discriminative representation for speaker verification can be extracted from verbal speech. However, how much speaker information that non-verbal vocalization carries is still a puzzle. This paper explores speaker verification based on the most ubiquitous form of non-verbal voice, laughter. First, we use a semi-automatic pipeline to collect a new Haha-Pod dataset from open-source podcast media. The dataset contains over 240 speakers' laughter clips with corresponding high-quality verbal speech. Second, we propose a Two-Stage Teacher-Student (2S-TS) framework to minimize the within-speaker embedding distance between verbal and non-verbal (laughter) signals. Considering Haha-Pod as a test set, two trials (S2L-Eval) are designed to verify the speaker's identity through laugh sounds. Experimental results demonstrate that our method can significantly improve the performance of the S2L-Eval test set with only a minor degradation on the VoxCeleb1 test set. The resources for the Haha-Pod dataset can be found at https://github.com/nevermoreLin/HahaPod.