Unsupervised Domain Adaptation with Multiple Acoustic Models.

机译：多声学模型的无监督域自适应。

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

We investigate the problem of adapting a recognition system with multiple acoustic models to a new domain in unsupervised mode. We compare maximum likelihood and discriminative approaches for unsupervised domain adaptation. Different adaptation data selection methods and adaptation strategies are investigated, using a baseline meeting recognition system and adaptation data from a congressional committee web site. Experiments show that one should avoid adapting all acoustic models to the same recognition output, and that ASR confidence estimates improve results when used for rejecting low-quality ASR output. The results show 8% relative overall improvement from unsupervised adaptation.

著录项

作者
Lei, X.; Wang, W.; Stolcke, A.;
展开▼
作者单位

展开▼
年度 2010
页码 1-7
总页数 7
原文格式 PDF
正文语种 eng
中图分类工业技术;
关键词
Acoustics; Maximum likelihood estimation; Adaptation; Base lines; Confidence level; Estimates; Internet; Models; Output; Quality; Recognition; Selection; Strategy; Domain adaptation; Discriminative adaptation;

机译：声学;最大似然估计;适应;基线;置信水平;估计;互联网;模型;产出;质量;识别;选择;战略;领域适应;判别适应;

相似文献

外文文献
中文文献
专利

1. Knowledge distillation methods for efficient unsupervised adaptation across multiple domains [J] . Nguyen-Meidine Le Thanh, Belal Atif, Kiran Madhu, Image and Vision Computing . 2021,第Apra期

机译：知识蒸馏方法，用于跨多个域的高效无监督适应
2. Unsupervised Speaker Adaptation Based on HMM Sufficient Statistics Using Multiple Acoustic Models Under Noisy Environment [J] . Randy Gomez, Akinobu Lee, Hiroshi Saruwatari, 電子情報通信学会技術研究報告. 音声. Speech . 2004,第542期

机译：噪声环境下基于HMM充分统计的多种声学模型的无监督说话人自适应
3. Unsupervised Speaker Adaptation Based on HMM Sufficient Statistics Using Multiple Acoustic Models Under Noisy Environment [J] . Randy GOMEZ, Akinobu LEE, Hiroshi SARUWATARI, 電子情報通信学会技術研究報告. 音声. Speech . 2004,第542期

机译：噪声环境下基于HMM充分统计的多种声学模型的无监督说话人自适应
4. Unsupervised domain adaptation with multiple acoustic models [C] . 2010 IEEE Spoken Language Technology Workshop . 2010

机译：具有多种声学模型的无监督域自适应
5. Learning Transferable Features for Unsupervised Domain Adaptation in Natural Language Processing [D] . Cui, Xia. 2020

机译：在自然语言处理中学习无监督域适应的可转移功能
6. Unsupervised Domain Adaptation With Optimal Transport in Multi-Site Segmentation of Multiple Sclerosis Lesions From MRI Data [O] . Antoine Ackaouy, Nicolas Courty, Emmanuel Vallée, 2020

机译：MRI数据对多发性硬化病变的多部位分割中具有最佳运输的无监督区域适应
7. Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training [O] . Teo Spadotto, Marco Toldo, Umberto Michieli, 2021

机译：无监督域适应多个域鉴别器和自适应自我培训

Unsupervised Domain Adaptation with Multiple Acoustic Models.

摘要

著录项

相似文献

相关主题

期刊订阅