Utterance-Level Methods for Identifying Reliable ASR-Output for Child Speech
This addresses the limitation of ASR for child speech in applications like language learning, though it is incremental as it builds on existing selection methods.
The paper tackled the problem of high ASR error rates in child speech applications by developing utterance-level methods to identify reliable ASR-outputs, achieving high precision (>97.4%) and enabling automatic selection of 21.0% to 55.9% of datasets with low error rates (<2.6% UER).
Automatic Speech Recognition (ASR) is increasingly used in applications involving child speech, such as language learning and literacy acquisition. However, the effectiveness of such applications is limited by high ASR error rates. The negative effects can be mitigated by identifying in advance which ASR-outputs are reliable. This work aims to develop two novel approaches for selecting reliable ASR-output at the utterance level, one for selecting reliable read speech and one for dialogue speech material. Evaluations were done on an English and a Dutch dataset, each with a baseline and finetuned model. The results show that utterance-level selection methods for identifying reliably transcribed speech recordings have high precision for the best strategy (P > 97.4) for both read speech and dialogue material, for both languages. Using the current optimal strategy allows 21.0% to 55.9% of dialogue/read speech datasets to be automatically selected with low (UER of < 2.6) error rates.