Addressing Cold Start Problem for End-to-end Automatic Speech Scoring
This addresses a specific issue for second-language speaking education systems, but it is incremental as it builds on existing self-supervised learning methods.
The paper tackles the cold start problem in end-to-end automatic speech scoring systems, where performance drops for new questions, by using prompt embeddings, question context embeddings, and pretrained acoustic models, and shows that the proposed framework improves robustness and outperforms baselines on TOEIC speaking test datasets.
Integrating automatic speech scoring/assessment systems has become a critical aspect of second-language speaking education. With self-supervised learning advancements, end-to-end speech scoring approaches have exhibited promising results. However, this study highlights the significant decrease in the performance of speech scoring systems in new question contexts, thereby identifying this as a cold start problem in terms of items. With the finding of cold-start phenomena, this paper seeks to alleviate the problem by following methods: 1) prompt embeddings, 2) question context embeddings using BERT or CLIP models, and 3) choice of the pretrained acoustic model. Experiments are conducted on TOEIC speaking test datasets collected from English-as-a-second-language (ESL) learners rated by professional TOEIC speaking evaluators. The results demonstrate that the proposed framework not only exhibits robustness in a cold-start environment but also outperforms the baselines for known content.