Skip to search form
Skip to main content
Skip to account menu
Semantic Scholar
Semantic Scholar's Logo
Search 218,524,450 papers from all fields of science
Search
Sign In
Create Free Account
Word error rate
Known as:
Error rate
, WER
, Word recognition rate
Word error rate (WER) is a common metric of the performance of a speech recognition or machine translation system. The general difficulty of…
Expand
Wikipedia
(opens in a new tab)
Create Alert
Alert
Related topics
Related topics
13 relations
BLEU
Cache language model
Edit distance
F1 score
Expand
Broader (2)
Evaluation of machine translation
Speech recognition
Papers overview
Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2017
Highly Cited
2017
Minimum Word Error Rate Training for Attention-Based Sequence-to-Sequence Models
Rohit Prabhavalkar
,
Tara N. Sainath
,
+4 authors
Anjuli Kannan
IEEE International Conference on Acoustics…
2017
Corpus ID: 20011126
Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to…
Expand
Highly Cited
2017
Highly Cited
2017
Optimizing Expected Word Error Rate via Sampling for Speech Recognition
Matt Shannon
Interspeech
2017
Corpus ID: 12653873
State-level minimum Bayes risk (sMBR) training has become the de facto standard for sequence-level training of speech recognition…
Expand
Highly Cited
2012
Highly Cited
2012
Application of Pretrained Deep Neural Networks to Large Vocabulary Speech Recognition
N. Jaitly
,
Patrick Nguyen
,
A. Senior
,
Vincent Vanhoucke
Interspeech
2012
Corpus ID: 13521651
The use of Deep Belief Networks (DBN) to pretrain Neural Networks has recently led to a resurgence in the use of Artificial…
Expand
Highly Cited
2011
Highly Cited
2011
Why word error rate is not a good metric for speech recognizer training for the speech translation task?
Xiaodong He
,
L. Deng
,
A. Acero
IEEE International Conference on Acoustics…
2011
Corpus ID: 14990591
Speech translation (ST) is an enabling technology for cross-lingual oral communication. A ST system consists of two major…
Expand
Highly Cited
2006
Highly Cited
2006
Word spotting for historical documents
T. Rath
,
R. Manmatha
International Journal of Document Analysis and…
2006
Corpus ID: 29159089
Searching and indexing historical handwritten collections are a very challenging problem. We describe an approach called word…
Expand
Highly Cited
2006
Highly Cited
2006
Error rate performance analysis of coded free-space optical links over gamma-gamma atmospheric turbulence channels
M. Uysal
,
T. Li
,
Meng Yu
IEEE Transactions on Wireless Communications
2006
Corpus ID: 10384926
Error control coding can be used over free-space optical (FSO) links to mitigate turbulence-induced fading. In this paper, we…
Expand
Highly Cited
2004
Highly Cited
2004
Error rate performance of coded free-space optical links over strong turbulence channels
M. Uysal
,
S. Navidpour
,
T. Li
IEEE Communications Letters
2004
Corpus ID: 6473890
Error control coding can be used over free-space optical (FSO) links to mitigate turbulence-induced fading. We present error rate…
Expand
Highly Cited
1999
Highly Cited
1999
Vector-based Natural Language Call Routing
Jennifer Chu-Carroll
,
Bob Carpenter
International Conference on Computational Logic
1999
Corpus ID: 14229502
This paper describes a domain-independent, automatically trained natural language call router for directing incoming calls in a…
Expand
Highly Cited
1998
Highly Cited
1998
Maximum likelihood modeling with Gaussian distributions for classification
R. Gopinath
Proceedings of the IEEE International Conference…
1998
Corpus ID: 2238572
Maximum likelihood (ML) modeling of multiclass data for classification often suffers from the following problems: (a) data…
Expand
Highly Cited
1995
Highly Cited
1995
Towards increasing speech recognition error rates
H. Bourlard
,
H. Hermansky
,
N. Morgan
Speech Communication
1995
Corpus ID: 17828677
By clicking accept or continuing to use the site, you agree to the terms outlined in our
Privacy Policy
(opens in a new tab)
,
Terms of Service
(opens in a new tab)
, and
Dataset License
(opens in a new tab)
ACCEPT & CONTINUE