A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit

2023/02/27 by Huh, Mina, Ray, Ruchira, Karnei, Corey · 1 citation
#Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2303.00510

Abstract

Data augmentations are known to improve robustness in speech-processing tasks. In this study, we summarize and compare different data augmentation strategies using S3PRL toolkit. We explore how HuBERT and wav2vec perform using different augmentation techniques (SpecAugment, Gaussian Noise, Speed Perturbation) for Phoneme Recognition (PR) and Automatic Speech Recognition (ASR) tasks. We evaluate model performance in terms of phoneme error rate (PER) and word error rate (WER). From the experiments, we observed that SpecAugment slightly improves the performance of HuBERT and wav2vec on the original dataset. Also, we show that models trained using the Gaussian Noise and Speed Perturbation dataset are more robust when tested with augmented test sets.

Cited by

• ArabEmoNet: A Lightweight Hybrid 2D CNN-BiLSTM Model with Attention for Robust Arabic Speech Emotion Recognition

Related

• Text Augmentation for Language Models in High Error Recognition Scenario
• Improving sequence-to-sequence speech recognition training with\n on-the-fly data augmentation
• persoDA: Personalized Data Augmentation for Personalized ASR
• Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation
• Does Speech enhancement of publicly available data help build robust Speech Recognition Systems?