List your company
ResearchFormerly WizWand

Automatic Speech Recognition on NIST CTS CallHome 2000

11WER2016 Microsoft system
10.67212.88615.117.314Sep 12, 2016Sep 17, 2016Sep 23, 2016Sep 29, 2016Oct 5, 2016Oct 11, 2016Oct 17, 2016
Updated 8mo ago

Evaluation results

MethodLinks
2016 Microsoft systemLanguage Model=Neural net LM2016.1011
Human transcription2016.1011.3
CombinationLanguage Model=Neural LM2016.0912
Saon et al. systemLanguage Model=Neural net LM2016.1012.2
Saon et al. CombinationLanguage Model=Neural LM2016.0912.2
ResNetLanguage Model=Neural LM2016.0913.2
2016 Microsoft systemLanguage Model=N-gram LM2016.1013.3
CombinationLanguage Model=N-gram LM2016.0913.3
LACELanguage Model=Neural LM2016.0913.5
Saon et al. systemLanguage Model=N-gram LM2016.1013.7
Saon et al. CombinationLanguage Model=N-gram LM2016.0913.7
ResNet GMM alignmentLanguage Model=Neural LM2016.0913.7
VGGLanguage Model=Neural LM2016.0914.1
27k Senone BLSTMLanguage Model=Neural LM2016.0914.6
ResNetLanguage Model=N-gram LM2016.0914.8
LACELanguage Model=N-gram LM2016.0914.8
Saon et al. LSTMLanguage Model=N-gram LM2016.1015.1
Saon et al. LSTMLanguage Model=N-gram LM2016.0915.1
Povey et al. LSTMLanguage Model=N-gram LM2016.1015.3
Povey et al. LSTMLanguage Model=N-gram LM2016.0915.3
ResNet GMM alignmentLanguage Model=N-gram LM2016.0915.3
BLSTMLanguage Model=Neural LM2016.0915.3
VGGLanguage Model=N-gram LM2016.0915.7
27k Senone BLSTMLanguage Model=N-gram LM2016.0916.2
BLSTMLanguage Model=N-gram LM2016.0916.7
300h ResNetLanguage Model=Neural LM, Training Data=300 hours2016.0917.7
300h ResNetLanguage Model=N-gram LM, Training Data=300 hours2016.0919.2