ISCA Archive Interspeech 2023
ISCA Archive Interspeech 2023

Accurate and Reliable Confidence Estimation Based on Non-Autoregressive End-to-End Speech Recognition System

Xian Shi, Haoneng Luo, Zhifu Gao, Shiliang Zhang, Zhijie Yan

Estimating confidence scores for recognition results is a classic task in ASR field and of vital importance for kinds of downstream tasks and training strategies. Previous end-to-end (E2E) based confidence estimation models (CEM) predict score sequences of equal length with input transcriptions, leading to unreliable estimation when deletion and insertion errors occur. In this paper we proposed CIF-Aligned confidence estimation model (CA-CEM) to achieve accurate and reliable confidence estimation based on novel non-autoregressive E2E ASR model - Paraformer. CA-CEM utilizes the modeling character of continuous integrate-and-fire (CIF) mechanism to generate token-synchronous acoustic embedding, which solves the estimation failure issue above. We measure the quality of estimation with AUC and RMSE in token level and ECE-U - a proposed metrics in utterance level. CA-CEM gains 24% and 19% relative reduction on ECE-U and also better AUC and RMSE on two test sets. Furthermore, we conduct analysis to explore the potential of CEM for different ASR related usage.