Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition-Reference-Cited by-同舟云学术

Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition

Published:2022-05-23 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Li Qiujia¹,Zhang Yu²,Qiu David²,He Yanzhang²,Cao Liangliang²,Woodland Philip C.¹

Affiliation:

1. University of Cambridge,UK

2. Google LLC,USA

Publisher

IEEE

Link

Reference38 articles.

1. On calibration of modern neural networks;guo;Proc ICML,2017

2. wav2vec 2.0: A framework for self-supervised learning of speech representations;baevski;Proc NeurIPS,2020

3. Pushing the limits of semi-supervised learning for automatic speech recognition;zhang;Proc NeurIPS SAS Workshop,2020

4. Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks;rousseau;Proc LREC,2014

5. TED-LIUM 3: Twice as much data and corpus repartition for experiments on speaker adaptation;hernandez;Proc Specom,2018

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Leveraging Confidence Models for Identifying Challenging Data Subgroups in Speech Models;2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW);2024-04-14