Confidence Estimation For Attention-based Sequence-to-sequence Models For Speech Recognition
2020 · Qiujia Li, David Qiu, Yu Zhang, et al.
Abstract
For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence scores can be reliably obtained from word posteriors in decoding lattices. However, for an ASR system with an auto-regressive decoder, such as an attention-based sequence-to-sequence model, computing word posteriors is difficult. An obvious alternative is to use the decoder softmax probability as the model confidence. In this paper, we first examine how some commonly used regularisation methods influence the softmax-based confidence scores and study the overconfident behaviour of end-to-end models. Then we propose a lightweight and effective approach named confidence estimation module (CEM) on top of an existing end-to-end ASR model. Experiments on LibriSpeech show that CEM can mitigate the overconfidence problem and can produce more reliable confidence s
Authors
(none)
Tags
Stats
Related papers
- Accurate And Reliable Confidence Estimation Based On Non-autoregressive End-to-end Speech Recognition System (2023)4.52
- An Evaluation Of Word-level Confidence Estimation For End-to-end Automatic Speech Recognition (2021)0.00
- Teles: Temporal Lexeme Similarity Score To Estimate Confidence In End-to-end ASR (2024)6.34
- Fast Entropy-based Methods Of Word-level Confidence Estimation For End-to-end Automatic Speech Recognition (2022)7.16
- Confidence Estimation For Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks (2019)8.35
- Sequence-level Confidence Classifier For ASR Utterance Accuracy And Application To Acoustic Models (2021)5.24
- Confidence Score Based Speaker Adaptation Of Conformer Speech Recognition Systems (2023)8.35
- Semantic-aware Confidence Calibration For Automated Audio Captioning (2025)0.00