Automatic Speech Recognition (ASR) for the Diagnosis of pronunciation of Speech Sound Disorders in Korean children
This work addresses the need for automated diagnostic tools in clinical settings for Korean children with speech sound disorders, though it is incremental as it builds on existing ASR models.
The study tackled the problem of diagnosing pronunciation issues in children with speech sound disorders by fine-tuning an ASR model to recognize speech as pronounced rather than as real words, achieving about 90% accuracy in matching human annotations.
This study presents a model of automatic speech recognition (ASR) designed to diagnose pronunciation issues in children with speech sound disorders (SSDs) to replace manual transcriptions in clinical procedures. Since ASR models trained for general purposes primarily predict input speech into real words, employing a well-known high-performance ASR model for evaluating pronunciation in children with SSDs is impractical. We fine-tuned the wav2vec 2.0 XLS-R model to recognize speech as pronounced rather than as existing words. The model was fine-tuned with a speech dataset from 137 children with inadequate speech production pronouncing 73 Korean words selected for actual clinical diagnosis. The model's predictions of the pronunciations of the words matched the human annotations with about 90% accuracy. While the model still requires improvement in recognizing unclear pronunciation, this study demonstrates that ASR models can streamline complex pronunciation error diagnostic procedures in clinical fields.