@InProceedings{Li2018_388,
<br/>   author = {Xinwei Li and Yue Pan and Matthew Gibson and Puming Zhan},
<br/>   booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2018},
<br/>   title = {DNN Online Adaptation for Automatic Speech Recognition},
<br/>   year = {2018},
<br/>   editor = {André Berton and Udo Haiber and Wolfgang Minker},
<br/>   month = mar,
<br/>   pages = {46--53},
<br/>   publisher = {TUDpress, Dresden},
<br/>   abstract  = {Although DNN-HMM based ASR systems can provide better accuracy than
GMM-HMM based ASR systems in general, their performance still suffers from
mismatches between the training and testing conditions. Online adaptation is a very
effective way to make an ASR system more robust to a variety of environments and
speaker characteristics. However, given large number of DNN parameters and only a
limited amount of adaptation data, it is very challenging to perform DNN online
adaptation effectively. In this paper, we propose two methods, namely i-vector and KLDivergence
regularized Linear Hidden Network, for performing DNN online adaptation
for real-time speech recognition systems. The proposed methods were evaluated on a
voice search data set. Over 3% relative word error rate reduction (WERR) was achieved
from each of the proposed methods alone. A further relative WERR of over 2% was
achieved from combining them.},
<br/>   isbn = {978-3-959081-28-3},
<br/>   issn = {0940-6832},
<br/>   keywords = {Signal Processing},
<br/>   url = {https://www.essv.de/pdf/2018_46_53.pdf},
<br/>}