Automatic Speech Recognition for Speech Assessment of Persian Preschool Children

TL;DR

This paper introduces a modified Wav2Vec 2.0 model with a new Random Frequency Pitch objective to improve speech recognition accuracy for Persian preschool children, especially in online assessments and low-data scenarios.

Contribution

The study proposes a novel RFP objective and fine-tunes the model on a new dataset for Persian speech, achieving superior WER and zero-shot performance.

Findings

Achieved a WER of 1.35 with masking and RFP on their dataset.

Reached a WER of 6.45 on Persian CommonVoice dataset.

Demonstrated effectiveness in zero- and few-shot learning scenarios.

Abstract

Preschool evaluation is crucial because it gives teachers and parents influential knowledge about children's growth and development. The COVID-19 pandemic has highlighted the necessity of online assessment for preschool children. One of the areas that should be tested is their ability to speak. Employing an Automatic Speech Recognition (ASR) system would not help since they are pre-trained on voices that differ from children's in terms of frequency and amplitude. Because most of these are pre-trained with data in a specific range of amplitude, their objectives do not make them ready for voices in different amplitudes. To overcome this issue, we added a new objective to the masking objective of the Wav2Vec 2.0 model called Random Frequency Pitch (RFP). In addition, we used our newly introduced dataset to fine-tune our model for Meaningless Words (MW) and Rapid Automatic Naming (RAN) tests. Using masking in concatenation with RFP outperforms the masking objective of Wav2Vec 2.0 by reaching a Word Error Rate (WER) of 1.35. Our new approach reaches a WER of 6.45 on the Persian section of the CommonVoice dataset. Furthermore, our novel methodology produces positive outcomes in zero- and few-shot scenarios.