Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition
This work addresses the challenge of reliable confidence estimation for downstream tasks in speech recognition when dealing with mismatched acoustic and linguistic conditions, though it is incremental as it builds on existing model-based confidence estimators.
The paper tackled the problem of confidence estimation for end-to-end speech recognition models on out-of-domain data, proposing methods that improved confidence metrics on TED-LIUM and Switchboard datasets while preserving in-domain performance.
As end-to-end automatic speech recognition (ASR) models reach promising performance, various downstream tasks rely on good confidence estimators for these systems. Recent research has shown that model-based confidence estimators have a significant advantage over using the output softmax probabilities. If the input data to the speech recogniser is from mismatched acoustic and linguistic conditions, the ASR performance and the corresponding confidence estimators may exhibit severe degradation. Since confidence models are often trained on the same in-domain data as the ASR, generalising to out-of-domain (OOD) scenarios is challenging. By keeping the ASR model untouched, this paper proposes two approaches to improve the model-based confidence estimators on OOD data: using pseudo transcriptions and an additional OOD language model. With an ASR model trained on LibriSpeech, experiments show that the proposed methods can greatly improve the confidence metrics on TED-LIUM and Switchboard datasets while preserving in-domain performance. Furthermore, the improved confidence estimators are better calibrated on OOD data and can provide a much more reliable criterion for data selection.