TY - GEN
T1 - Improvement of automatic english pronunciation assessment with small number of utterances using sentence speakability
AU - Naijo, Satsuki
AU - Ito, Akinori
AU - Nose, Takashi
N1 - Funding Information:
Part of this work was supported by JSPS KAKENHI JP17H00823.
Publisher Copyright:
Copyright © 2021 ISCA.
PY - 2021
Y1 - 2021
N2 - The current Computer-Assisted Pronunciation Training (CAPT) system uses DNN-based speech recognition results to evaluate learner's pronunciation with high accuracy when using many utterances for the evaluation. However, when we use only a few utterances, the accuracy of the CAPT system deteriorates. One reason for the deterioration is that the score calculated by a CAPT system is biased depending on the pronunciation diffi- culty of the sentences when using a small number of utterances. In this study, we developed a CAPT system that takes the sen- tence speakability (pronunciation difficulty of sentences) into account. As a result, the correlation coefficient between the human evaluation and the machine score was 0.46 in the con- ventional method, while it improved to 0.57 with the proposed method.
AB - The current Computer-Assisted Pronunciation Training (CAPT) system uses DNN-based speech recognition results to evaluate learner's pronunciation with high accuracy when using many utterances for the evaluation. However, when we use only a few utterances, the accuracy of the CAPT system deteriorates. One reason for the deterioration is that the score calculated by a CAPT system is biased depending on the pronunciation diffi- culty of the sentences when using a small number of utterances. In this study, we developed a CAPT system that takes the sen- tence speakability (pronunciation difficulty of sentences) into account. As a result, the correlation coefficient between the human evaluation and the machine score was 0.46 in the con- ventional method, while it improved to 0.57 with the proposed method.
KW - Computer-assisted pronunciation training
KW - Sentence speakability
KW - Speech recognition
UR - http://www.scopus.com/inward/record.url?scp=85119522312&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119522312&partnerID=8YFLogxK
U2 - 10.21437/Interspeech.2021-1132
DO - 10.21437/Interspeech.2021-1132
M3 - Conference contribution
AN - SCOPUS:85119522312
T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
SP - 101
EP - 105
BT - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
PB - International Speech Communication Association
T2 - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Y2 - 30 August 2021 through 3 September 2021
ER -