scispace - formally typeset
Search or ask a question
Topic

Word error rate

About: Word error rate is a research topic. Over the lifetime, 11939 publications have been published within this topic receiving 298031 citations.


Papers
More filters
Patent
29 Jul 1992
TL;DR: In this article, the redundancy due to the use of the convolutional codes as the error correction codes is reduced by using a convolution encoding at an identical encoding rate and a puncture process using different puncture rates for different classes of the input signals classified by the error sensitivity of each bit.
Abstract: A reduction of the redundancy due to the use of the convolutional codes as the error correction codes is achieved by a convolutional encoding at an identical encoding rate and a puncture process using different puncture rates for different classes of the input signals classified by the error sensitivity of each bit. A reduction of the decoding delay time without deteriorating the decoding error rate is achieved by updating the survivor path by remaining bits of the selected survivor path for each state other than the oldest bit and an additional bit indicative of the each state to which a transition is made at the present stage of decoding. A reduction of a circuit size of a Viterbi decoder is achieved by using a single RAM for memorizing a path metric and a survivor path for each state at an immediately previous stage of decoding together in each word of the memory capacity. A reduction of the decoding error rate for the data block encoded by the convolutional encoding is achieved by using the (i+N+j) bits of decoder input signals containing entire N bits of the received signals, preceded by last i bits of the received signals and followed by first j bits of the received signals.

68 citations

Proceedings Article
02 Jun 2010
TL;DR: It is shown that Meteor-next improves correlation with HTER over baseline metrics, including earlier versions of Meteor, and approaches the correlation level of a state-of-the-art metric, TER-plus (TERp).
Abstract: This paper presents Meteor-next, an extended version of the Meteor metric designed to have high correlation with post-editing measures of machine translation quality. We describe changes made to the metric's sentence aligner and scoring scheme as well as a method for tuning the metric's parameters to optimize correlation with human-targeted Translation Edit Rate (HTER). We then show that Meteor-next improves correlation with HTER over baseline metrics, including earlier versions of Meteor, and approaches the correlation level of a state-of-the-art metric, TER-plus (TERp).

68 citations

Proceedings ArticleDOI
25 Aug 1996
TL;DR: This article presents a novel approach to estimating the Bayes error based on classifier combining techniques, and finds that the combiner-based estimate outperforms the classical methods.
Abstract: The Bayes error provides the lowest achievable error rate for a given pattern classification problem. There are several classical approaches for estimating or finding bounds for the Bayes error. One type of approach focuses on obtaining analytical bounds, which are both difficult to calculate and dependent on distribution parameters that may not be known. Another strategy is to estimate the class densities through non-parametric methods, and use these estimates to obtain bounds on the Bayes error. This article presents a novel approach to estimating the Bayes error based on classifier combining techniques. For an artificial data set where the Bayes error is known, the combiner-based estimate outperforms the classical methods.

68 citations

Proceedings ArticleDOI
Justinian Rosca1, Radu Balan1, N.P. Fan1, C. Beaugeant2, V. Gilg2 
30 Aug 2002
TL;DR: A novel multichannel source activity detector that exploits the spatial localization of the target audio source that uses an array signal processing technique to maximize the signal-to-interference ratio for the target source thus decreasing the activity detection error rate.
Abstract: Detecting when voice is or is not present is an outstanding problem for speech transmission, enhancement and recognition. Here we present a novel multichannel source activity detector that exploits the spatial localization of the target audio source. The detector uses an array signal processing technique to maximize the signal-to-interference ratio for the target source thus decreasing the activity detection error rate. We compare our two-channel voice activity detector (VAD) with the AMR voice detection algorithms on real data recorded in a noisy car environment. The new algorithm shows improvements in error rates of 55–70% compared to the state-of-the-art adaptive multi-rate algorithm AMR2 used in present voice transmission technology.

68 citations

Journal ArticleDOI
TL;DR: This paper presents the multivaRiate gAussian-based cepsTral normaliZation (RATZ) family of algorithms which modify incoming cepstral features, along with the STAR (STAtistical Reestimation)family of algorithms, which modify the internal statistics of the classifier.

68 citations


Network Information
Related Topics (5)
Deep learning
79.8K papers, 2.1M citations
88% related
Feature extraction
111.8K papers, 2.1M citations
86% related
Convolutional neural network
74.7K papers, 2M citations
85% related
Artificial neural network
207K papers, 4.5M citations
84% related
Cluster analysis
146.5K papers, 2.9M citations
83% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023271
2022562
2021640
2020643
2019633
2018528