| 1 |
Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition ...
|
|
|
|
Abstract:
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 ... : Accepted as a conference paper at ICASSP 2022 ...
|
|
Keyword:
Audio and Speech Processing eess.AS; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/2110.03327
https://dx.doi.org/10.48550/arxiv.2110.03327
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
