Speech Recognition on swb_hub_500 WER fullSWBCH

Metric: Percentage error (lower is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Percentage error▲	Extra Data	Paper	Date↕	Code
1	IBM (LSTM+Conformer encoder-decoder)	6.8	No	On the limit of English conversational speech re...	2021-05-03	-
2	IBM (LSTM encoder-decoder)	7.8	No	Single headed attention based sequence-to-sequen...	2020-01-20	-
3	ResNet + BiLSTMs acoustic model	10.3	No	English Conversational Telephone Speech Recognit...	2017-03-06	-
4	VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+Broadcast	11.9	No	The Microsoft 2016 Conversational Speech Recogni...	2016-09-12	-
5	RNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + "model M" + NNLM language model	12.2	No	The IBM 2016 English Conversational Telephone Sp...	2016-04-27	-
6	HMM-BLSTM trained with MMI + data augmentation (speed) + iVectors + 3 regularizations + Fisher	13	No	-	-	-
7	HMM-TDNN trained with MMI + data augmentation (speed) + iVectors + 3 regularizations + Fisher (10% / 15.1% respectively trained on SWBD only)	13.3	No	-	-	-
8	CNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWB	16	No	Deep Speech: Scaling up end-to-end speech recogn...	2014-12-17	Code
9	HMM-TDNN + iVectors	17.1	No	-	-	-
10	HMM-DNN +sMBR	18.4	No	-	-	-
11	DNN + Dropout	19.1	No	Building DNN Acoustic Models for Large Vocabular...	2014-06-30	Code
12	HMM-TDNN + pNorm + speed up/down speech	19.3	No	-	-	-

#1IBM (LSTM+Conformer encoder-decoder)SOTA
6.8
Percentage error· 2021-05-03
On the limit of English conversational speech recognition
#2IBM (LSTM encoder-decoder)SOTA
7.8
Percentage error· 2020-01-20
Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard
#3ResNet + BiLSTMs acoustic modelSOTA
10.3
Percentage error· 2017-03-06
English Conversational Telephone Speech Recognition by Humans and Machines
#4VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+BroadcastSOTA
11.9
Percentage error· 2016-09-12
The Microsoft 2016 Conversational Speech Recognition System
#5RNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + "model M" + NNLM language modelSOTA
12.2
Percentage error· 2016-04-27
The IBM 2016 English Conversational Telephone Speech Recognition System
#6HMM-BLSTM trained with MMI + data augmentation (speed) + iVectors + 3 regularizations + Fisher
13
Percentage error
No paper
#7HMM-TDNN trained with MMI + data augmentation (speed) + iVectors + 3 regularizations + Fisher (10% / 15.1% respectively trained on SWBD only)
13.3
Percentage error
No paper
#8CNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWBSOTA
16
Percentage error· 2014-12-17
Deep Speech: Scaling up end-to-end speech recognition Code
#9HMM-TDNN + iVectors
17.1
Percentage error
No paper
#10HMM-DNN +sMBR
18.4
Percentage error
No paper
#11DNN + DropoutSOTA
19.1
Percentage error· 2014-06-30
Building DNN Acoustic Models for Large Vocabulary Speech Recognition Code
#12HMM-TDNN + pNorm + speed up/down speech
19.3
Percentage error
No paper