Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

5

ACL
2003

favoriteEmaildiscussreport

103views Computational Linguistics» more ACL 2003»

Classifying Recognition Results for Spoken Dialog Systems

13 years 5 months ago

Classifying Recognition Results for Spoken Dialog Systems

Download acl.ldc.upenn.edu

This paper investigates the correlation between acoustic conﬁdence scores as returned by speech recognizers with recognition quality. We report the results of two machine learning experiments that predict the word error rate of recognition hypotheses and the conﬁdence error rate for individual words within them.

Malte Gabsdil

Real-time Traffic

ACL 2003 | ACL 2007 | Conﬁdence Error Rate | Error Rate | Word Error Rate |

claim paper

Related Content

» Estimation Method of User Satisfaction Using Ngrambased Dialog History Model for Spoken Di...

» Three phase verification for spoken dialog clarification

» DialogStudio A workbench for datadriven spoken dialog system development and management

» Partially observable Markov decision processes for spoken dialog systems

» Dialog in the open world platform and applications

» A Statistical User Simulation Technique for the Improvement of a Spoken Dialog System

» Dialog Navigator A Spoken Dialog QA System based on Large Text Knowledge Base

» Automatic Detection of Nonreferential It in Spoken MultiParty Dialog

» From rulebased to statistical grammars Continuous improvement of largescale spoken dialog ...

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2003
Where	ACL
Authors	Malte Gabsdil

Comments (0)