List your company
ResearchFormerly WizWand

Automatic Speech Recognition on Tuda-DE (test)

10WERIMS-Speech
8.57818.176527.77537.3735Jul 26, 2018Nov 23, 2018Mar 23, 2019Jul 22, 2019Nov 19, 2019Mar 18, 2020Jul 17, 2020
Updated 8mo ago

Evaluation results

MethodLinks
IMS-SpeechScored utterances=3481 of 4100 (85%)2019.0810
IMS-SpeechLanguage=German2019.0812
Google APIScored utterances=3481 of 4100 (85%)2019.0812.4
TransformerTraining Datasets=TD, SW*, LV*, Training data hours (h)=1460, LM=RNNLM (4 x 1024), Alignment=CTC-segmentation2020.0712.8
TDNN-HMMTraining Data=Tuda-De + SWC (min. pruned), Vocabulary=350,029, LM=4-gram KN + 2-layer LSTM LM2018.0714.38
TDNN-HMMTraining Datasets=TD, SW, MA, Training data hours (h)=412, LM=LSTM (2 x 1024)2020.0714.4
State of the artLanguage=German2019.0814.4
TransformerTraining Datasets=TD, SW*, LV*, Training data hours (h)=1460, LM=RNNLM (2 x 650), Alignment=CTC-segmentation2020.0714.9
TransformerTraining Datasets=TD, SW, CV, Training data hours (h)=986, LM=RNNLM (4 x 1024)2020.0715.2
TDNN-HMMTraining Datasets=TD, SW, CV, Training data hours (h)=649, LM=4-gram KN2020.0715.9
TDNN-HMMTraining Data=Tuda-De + SWC (min. pruned), Vocabulary=350,029, LM=4-gram KN2018.0716.49
TDNN-HMMTraining Datasets=TD, SW, MA, Training data hours (h)=412, LM=4-gram KN2020.0716.5
TransformerTraining Datasets=TD, SW, CV, Training data hours (h)=986, LM=RNNLM (2 x 650)2020.0717.1
TransformerTraining Datasets=TD, SW, CV, Training data hours (h)=649, LM=RNNLM (2 x 650)2020.0717.2
TDNN-HMMTraining Data=Tuda-De + SWC (min. pruned), Vocabulary=182,784, LM=3-gram KN2018.0719.6
TransformerTraining Datasets=TD, SW*, LV*, Training data hours (h)=1460, LM=None, Alignment=CTC-segmentation2020.0719.7
TDNN-HMMTraining Data=Tuda-De + SWC (min. pruned), Vocabulary=126,794, LM=3-gram KN2018.0721.43
TDNN-HMMTraining Data=Tuda-De + SWC (cons. pruned), Vocabulary=126,794, LM=3-gram KN2018.0722.22
GMM-HMMTraining Data=Tuda-De + SWC (min. pruned), Vocabulary=350,029, LM=4-gram KN2018.0725.77
GMM-HMMTraining Data=Tuda-De + SWC (min. pruned), Vocabulary=182,784, LM=3-gram KN2018.0728.25
TDNN-HMMTraining Data=Tuda-De, Vocabulary=126,794, LM=3-gram KN2018.0728.96
GMM-HMMTraining Data=Tuda-De + SWC (min. pruned), Vocabulary=126,794, LM=3-gram KN2018.0730.99
GMM-HMMTraining Data=Tuda-De + SWC (cons. pruned), Vocabulary=126,794, LM=3-gram KN2018.0731.06
TDNN-HMMTraining Data=Tuda-De, Vocabulary=28,131, LM=3-gram KN2018.0736.32
GMM-HMMTraining Data=Tuda-De, Vocabulary=126,794, LM=3-gram KN2018.0738.34
GMM-HMMTraining Data=Tuda-De, Vocabulary=28,131, LM=3-gram KN2018.0745.55