Utterance-level selection methods identify reliable ASR outputs for child speech with precision above 97.4 percent, enabling 21 to 55.9 percent of read and dialogue datasets to be retained with utterance error rates below 2.6 percent across English and Dutch.
Utterance-Level Methods for Identifying Reliable ASR-Output for Child Speech
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Utterance-Level Methods for Identifying Reliable ASR-Output for Child Speech
Utterance-level selection methods identify reliable ASR outputs for child speech with precision above 97.4 percent, enabling 21 to 55.9 percent of read and dialogue datasets to be retained with utterance error rates below 2.6 percent across English and Dutch.