Fast Entropy-based Methods Of Word-level Confidence Estimation For End-to-end Automatic Speech Recognition

Abstract

This paper presents a class of new fast non-trainable entropy-based confidence estimation methods for automatic speech recognition. We show how per-frame entropy values can be normalized and aggregated to obtain a confidence measure per unit and per word for Connectionist Temporal Classification (CTC) and Recurrent Neural Network Transducer (RNN-T) models. Proposed methods have similar computational complexity to the traditional method based on the maximum per-frame probability, but they are more adjustable, have a wider effective threshold range, and better push apart the confidence distributions of correct and incorrect words. We evaluate the proposed confidence measures on LibriSpeech test sets, and show that they are up to 2 and 4 times better than confidence estimation based on the maximum per-frame probability at detecting incorrect words for Conformer-CTC and Conformer-RNN-T models, respectively.

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keylaptev2022fast

Related papers

• An Evaluation Of Word-level Confidence Estimation For End-to-end Automatic Speech Recognition (2021)0.00
• Accurate And Reliable Confidence Estimation Based On Non-autoregressive End-to-end Speech Recognition System (2023)4.52
• Confidence Estimation For Attention-based Sequence-to-sequence Models For Speech Recognition (2020)11.49
• Utterance-level Neural Confidence Measure For End-to-end Children Speech Recognition (2021)6.77
• Adamer-ctc: Connectionist Temporal Classification With Adaptive Maximum Entropy Regularization For Automatic Speech Recognition (2024)5.84
• Confidence Estimation For Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks (2019)8.35
• Semantic-aware Confidence Calibration For Automated Audio Captioning (2025)0.00
• Teles: Temporal Lexeme Similarity Score To Estimate Confidence In End-to-end ASR (2024)6.34