End-to-End and Self-Supervised Learning for ComParE 2022 Stuttering Sub-Challenge
In this paper, we present end-to-end and speech embedding based systems trained in a self-supervised fashion to participate in the ACM Multimedia 2022 ComParE Challenge, specifically the stuttering sub-challenge. In particular, we exploit the embeddings from the pre-trained Wav2Vec2.0 model for stuttering detection (SD) on the KSoF dataset. After embedding extraction, we benchmark with several methods for SD. Our proposed self-supervised based SD system achieves a UAR of 36.9 which is 31.32 (DeepSpectrum) challenge baseline (CBL). Moreover, we show that concatenating layer embeddings with Mel-frequency cepstral coefficients (MFCCs) features further improves the UAR of 33.81 respectively over the CBL. Finally, we demonstrate that the summing information across all the layers of Wav2Vec2.0 surpasses the CBL by a relative margin of 45.91 Computational Paralinguistics ChallengE
READ FULL TEXT